# Research Papers — 2026-06 · bundle page 78 of 260 > Full-text markdown of papers #3851–3900 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/78 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/77.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/79.md) ### Learning Moral Diversity: Modelling Individual Perspectives in Moral Classification of Texts Authors: Yi Ren, Lewis Mitchell, Matthew Roughan Published: 2026-06-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.22771v1 Understanding moral values in social media text offers insight into moral judgement formation, and supervised NLP models trained on crowdsourced data have achieved strong classification performance. However, most approaches simplify the problem by aggregating multiple annotators' labels into a single "ground truth", overlooking the inherent subjectivity of the task. In practice, there are disagreements between annotators caused by personal viewpoint or inherent ambiguities, particularly for short tweets. Here, we extend a pretrained language model with a layer that learns annotator-specific features. Our model improves predictions of individual annotations and yields representations that reveal meaningful insights into annotators' moral perspectives. We show that models trained on aggregated labels may hide variation and give a misleading impression of performance. Overall, we demonstrate that disagreement reflects the inherent subjectivity of the task and that modelling individual perspectives creates benefits for moral classification of texts. --- ### Statistical Matching via Schrödinger Bridge beyond Conditional Independence Authors: Eunho Koo, Tongseok Lim, Jinwon Sohn Published: 2026-06-22 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2606.22770v1 Statistical matching combines partially overlapping datasets that share covariates $X$ but observe the target $Y$ and auxiliary variables $Z$ separately. Classical approaches typically invoke the conditional independence assumption (CIA), which makes the problem identifiable but fundamentally implies that the imported auxiliary variable provides no additional predictive power for $Y$ once $X$ is known. To capture this latent $Y$--$Z$ dependence, we propose a novel dependency-aware Schrödinger bridge for predictive statistical matching. Our approach couples the two separated databases by tilting the conservative CIA baseline with a transportation-based compatibility cost, recovering an informative joint distribution. The resulting statistical learning framework yields full probabilistic posterior rules for bidirectional imputation. Theoretically, we establish a sufficient condition under which the learned bridge strictly improves over the CIA baseline, alongside an exact joint recovery guarantee in the Gaussian setting under an appropriate cost. Across synthetic benchmarks and real-world datasets (CelebA and Adult), we demonstrate that our dependency-aware completion consistently improves downstream predictive utility, proving especially beneficial in settings like data recoding where the underlying population exhibits strong $Y$--$Z$ dependence. --- ### Noise is Signal: Density-Based Outliers as Leading Indicators of Occupational Emergence in Labor Market Text Authors: Shreyash Rawat Published: 2026-06-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.22769v1 Standard NLP pipelines for occupational clustering discard the 10-15% of job postings that density-based methods assign to noise. We argue this is an error: in rapidly evolving domains, low posting density signals novelty, not incoherence. We formalize this as the Emergence-Density Inversion (EDI) hypothesis and test it longitudinally on 84,988 job postings across eight quarters (Q4 2022-Q3 2024). EDI is partially confirmed: high-EOS outlier groups transition to stable clusters in 1.4 +/- 0.6 quarters vs. 4.1 +/- 1.2 for low-EOS groups (p < 0.001), though the signal fails in approximately 19% of cases, which we characterize as a failure analysis. We extend the Emerging Occupation Score (EOS) with Temporal Velocity and Cross-Platform Convergence, improving 2-quarter cluster-formation prediction from F1 = 0.61 to 0.74, outperforming Isolation Forest, LOF, GLOSH, and BERTrend baselines. A retrospective study on three now-established roles (MLOps Engineer, DevOps/SRE, Data Engineer) confirms EOS signalled 2-3 quarters before cluster formation, providing held-out validation. A held-out annotator panel (kappa = 0.74) rates EOS > 0.75 as coherent emerging occupations with 77% precision. Prompt Engineer, AI Safety Researcher, Foundation Model Engineer, and Agent Systems Engineer, all absent from O*NET, are top-4 in Q3 2024 and form stable clusters by Q1 2025. --- ### Factored Gossip DiLoCo: Reducing Blocking Communication in DiLoCo Authors: Chamin Hewa Koneputugodage, Thalaiyasingam Ajanthan, Sameera Ramasinghe, Hadi Mohaghegh Dolatabadi, Shamane Siriwardhana, Gil Avraham, Violetta Shevchenko, Karol Pajak, James Snewin, Alexander Long Published: 2026-06-22 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2606.22768v1 To make large-scale distributed training practical outside high-bandwidth datacenters, we must reduce blocking, high-volume synchronization. While DiLoCo communicates infrequently, its outer synchronization remains bandwidth-heavy and brittle to stragglers and transient failures. We relax exact synchronization to approximate synchronization via mixing/gossip, which degrades gracefully under delays and communication failures. This allows us to factorize DiLoCo synchronization into a non-blocking mixing step that overlaps computation with no staleness, and a blocking mixing step that tightens worker agreement, yielding a tunable trade-off between compute utilization and optimization stability. On up to billion-parameter language models in low-bandwidth settings, our framework substantially improves compute utilization compared to DiLoCo, with training progress ranging from comparable to closely matching it, and is more robust to failures. --- ### READ More than What You See: Reinforcement Learning for Accurate and Coherent Audio Description Generations Authors: Bo Fang, Xinyao Zhang, Yuxin Song, Hui Zhang, Hang Zhou, Antoni B. Chan Published: 2026-06-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.22766v1 Audio Description aims to generate concise narrations of essential visual content in audio-visual media for blind and low-vision audiences. Existing methods either rely on prompting off-the-shelf multimodal models, which often mismatch AD style, or partially optimize training-based systems with next-token prediction, which under-explores model capacity and biases generation toward generic expressions. We present READ, the first reinforcement-learning (RL) framework for training-based AD generation. READ formulates AD as sequence-level optimization with reference-matching, length, and format rewards, and further introduces a dedicated coherence reward under context-aware supervision to promote narratively coherent descriptions. Experiments on MAD-Eval, CMD-AD, and TV-AD show that READ substantially outperforms prior methods across diverse evaluation metrics. Our results highlight RL as a promising paradigm for accurate and coherent AD generation. Our codes, models, and benchmark results will be publicly available. --- ### Evolutionary Optimization Reveals Structural Constraints on Reservoir Architecture for Spatiotemporal Chaos Authors: Nima Dehghani Published: 2026-06-22 Categories: cs.NE, cs.AI, cs.LG, nlin.CD, physics.comp-ph arXiv: https://arxiv.org/abs/2606.22765v1 Biological systems maintain function in fluctuating environments by transforming past stimulation into internal dynamical states that support future-oriented responses. Reservoir computing provides a computational analogue, but standard formulations often treat the recurrent substrate as a fixed random network and train only the readout. Here we ask how the substrate itself changes when reservoir architecture is placed under evolutionary selection for prediction. Using the Kuramoto--Sivashinsky equation as a testbed for spatiotemporal chaos, we evolved reservoirs over five construction hyperparameters: size, connectivity degree, spectral radius, input scaling, and readout regularization. Evolution reduced prediction error at the population level, extended the low-error forecast horizon, and organized the design space along a diminishing-return size--efficiency frontier. Structural analyses showed that evolved reservoirs remained within a conserved stochastic-block-model-like spectral envelope while refining low-eigenvalue modes, locking modularity to an intermediate band, and pruning connection cost within that band. Pareto analysis showed that elite reservoirs occupied a horizontal floor in the cost--modularity plane, indicating that accuracy and efficiency were achieved jointly rather than through a simple trade-off. These findings show that evolutionary optimization does not merely improve prediction, but exposes interpretable structural constraints on the recurrent substrate: it stabilizes a task-suitable dynamical class and refines the architectural degrees of freedom most relevant for prediction. Evolutionary reservoir computing therefore provides a bio-inspired framework for studying how predictive demands shape adaptive dynamical networks. --- ### HERCULES: An Open-Source Simulation Framework for Heterogeneous Multi-Robot SLAM, Collaborative Perception, and Exploration Authors: Sandilya Sai Garimella, Daniel Chase Butterfield, Sean Wilson, Lu Gan Published: 2026-06-22 Categories: cs.RO, cs.CV, cs.MA, eess.SY arXiv: https://arxiv.org/abs/2606.22756v1 We present HERCULES, an open-source simulator and data-collection pipeline for heterogeneous multi-robot autonomy. Built upon the Unreal Engine 5 (UE5)-based simulators AirSim and Cosys-AirSim, HERCULES resolves key architectural limitations of prior frameworks to enable concurrent unmanned aerial and ground vehicle (UAV-UGV) operation in large-scale, photorealistic, dynamic environments. It introduces a new waypoint-tracking UGV controller that mirrors existing UAV control interfaces, and provides a shared navigation stack for mapping, traversability analysis, planning, and control across heterogeneous platforms. Expanding inherited sensor suites, it adds physics-based long-wave infrared (LWIR) cameras and configurable night-vision modes for degraded visual environments. HERCULES provides lightweight APIs, ROS 2 wrappers, and rigorous time synchronization across sensors and platforms, and brings state-of-the-art game-engine capabilities into robotics simulation, integrating intelligent agents such as pedestrians, traffic, and wildlife with high-fidelity dynamic phenomena, including fire, flooding, and crop disease spread. HERCULES runs in two modes: passively, replaying offline-designed trajectories to generate reproducible multi-modal datasets, and actively, running an online planner in closed loop from live observations. Our experiments in heterogeneous multi-robot SLAM, collaborative perception, and exploration, using both HERCULES-generated data and active closed-loop execution, demonstrate its utility for advancing heterogeneous multi-robot autonomy. We publicly release our source code, experiment code, documentation, and datasets, including a heterogeneous multi-robot SLAM benchmark collected with two UAVs and two UGVs across kilometer-scale desert, forest, and city environments, at https://lunarlab-gatech.github.io/HERCULES-website. --- ### One-Step Flow Matching for Generative Modeling of Path-Dependent Physical Fields Authors: Yijing Zhou, Jasmin Jelovica Published: 2026-06-22 Categories: cs.LG, cs.CE, physics.comp-ph arXiv: https://arxiv.org/abs/2606.22752v1 Physical simulations for intricate geometries with path-dependent constitutive models face difficulties due to the enormous computational cost they require. Recently, the emergence of generative AI models, which succeed in image and video synthesis tasks, has provided a promise to further improve simulations. Although U-Net-based denoising diffusion probabilistic models (DDPMs) have been adopted for elastic stress field generation, they typically require hundreds of sampling steps, and applications of generative models to path-dependent, e.g. plastic, stress fields remain very limited. In this work, we propose a novel flow matching (FM) model based on a transformer backbone for high-resolution path-dependent stress field generation with stochastic loading-unloading paths and geometry. The proposed model operates within the latent space of a variational autoencoder (VAE) and formulates the simulation of plastic fields as a video synthesis task, directly generating the stress fields across all time steps. Meanwhile, we design a non-Gaussian source distribution for flow matching, such that crossings among conditional transport paths are reduced during training. This enables our model to generate satisfactory samples in one step without relying on distillation. In addition, we introduce token-level loading embeddings and two auxiliary networks to further enhance the model performance in path-dependent simulation. The results demonstrate that, even with a limited training dataset, our model can accurately generate high-resolution path-dependent fields. It is much more computationally efficient than finite element analysis, providing a speedup of 6 to 7 times over FEM on CPUs and approximately two orders of magnitude speedup on consumer-grade GPUs. --- ### RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation Authors: Yuchuan Ding, Linfei Li, Lin Zhang, Ying Shen Published: 2026-06-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.22749v1 Pre-trained Vision Foundation Models (VFMs) have become central to modern computer vision due to their powerful semantic representations and strong generalization ability. However, their patchified or pooled outputs are inherently low-resolution, limiting their effectiveness in tasks requiring fine-grained, pixel-level reasoning. Existing feature upsampling approaches either degrade semantic fidelity or rely on VFM-specific retraining and heavy architectures, hindering efficiency and scalability. To address these challenges, we propose RaysUp, an ultra-lightweight, task-agnostic, and VFM-agnostic feature upsampling framework that reconstructs high-resolution feature maps at arbitrary resolutions. Unlike conventional 2D interpolation or attention-based schemes, RaysUp lifts feature reconstruction into a geometry-aware ray domain. Specifically, we introduce a Spatially Decoupled Guidance Encoder for direction-aware guidance encoding, an Any-Resolution Cross-Attention mechanism for resolution-flexible reconstruction, and a novel Ray Positional Encoding (RayPE) that injects implicit 3D geometric priors via 6D Plucker ray coordinates. Finally, a Geometry-Aware Neighborhood Attention module further ensures content-adaptive bilateral aggregation while preserving geometric consistency. Extensive experiments across diverse dense prediction tasks demonstrate that RaysUp achieves state-of-the-art performance while using only 16% of the parameters of AnyUp and delivering approximately 7x faster inference. These results highlight a substantially improved accuracy-efficiency trade-off and establish RaysUp as a practical and scalable solution for universal feature upsampling. Code is available at https://github.com/MAP-RaysUp/RaysUp. --- ### AI Fiction in the Wild Authors: Neel Gupta, Maria Antoniak, Melanie Walsh Published: 2026-06-22 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2606.22748v2 Some professional authors are beginning to use AI tools to help produce their fiction writing. Are readers using AI to generate fiction, too? Drawing on over 500,000 anonymized, English-language ChatGPT-user conversations (arXiv:2405.01470), we find that more than one third of the conversations involve some form of fiction generation -- including original stories, roleplay, fanfiction, and erotica. This AI-generated fiction is notably dominated by power users. We identify common fiction generation patterns and profiles among these users, including what we call "infinite story demanders," who repeatedly request and revise variations of the same or similar narratives over extended periods of time. We show that users especially gravitate toward fanfiction and erotica, and that they are broadly drawn to generic forms, repetition, immediacy, and niche combinations of story elements. Our findings motivate two theoretical provocations. First, we argue that AI technologies may lead to a shift in the conventional relationship between the author and reader, potentially producing what we call a "solipsistic reader-writer," who both generates and consumes fiction within a closed conversational loop, interacting with a machine rather than a human other. Second, we note that LLMs enable interactivity, play, and permutation in ways that are seemingly pleasurable for users, raising questions about where AI will fit into contemporary storytelling and entertainment ecosystems. We situate these developments within broader transformations in literature and media, including self-publishing, fanfiction, and pornography, and suggest that AI-generated fiction shares structural affinities with on-demand, personalized, and repetitive cultural forms. --- ### Language-Specific Sentiment Polarity Biases in Encoder and Large Language Model Classification of Product Reviews Authors: Advita Rajiv, Kavitha Kothur, Gautham Reddy Published: 2026-06-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.22745v1 This study investigates sentiment polarity biases, specifically, differences in how accurately AI models classify positive versus negative reviews across languages and model architectures. Large language models show a negative bias in French and are more accurate on negative reviews, while encoder models exhibit positive bias in Japanese, missing negative reviews that use indirect criticism. These language-specific polarity biases have implications in both social and business domains deploying multilingual sentiment analysis systems. --- ### Error Highways: Scaling Predictive Coding to Very Deep Networks Authors: Amirhossein Mohammadi, Alexander G. Ororbia Published: 2026-06-22 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2606.22744v1 Predictive coding networks (PCNs) offer a biologically-plausible, local-learning alternative to back-propagation of errors (backprop). Nevertheless, they have remained largely confined to shallow architectures and evaluated on simple machine intelligence benchmarks. A central obstacle to scaling PCNs is that the learning signal decays rapidly as it propagates away from the clamped boundaries, leaving interior layers effectively unchanged. To directly counter this problem, we propose highway error propagation (HEP), a scheme that augments the free energy function underlying predictive coding (PC) by altering its neural structure with feedback matrices $V_{L\to i}$ that couple selected hidden states directly to the clamped output error. Since this coupling is linear in the hidden state, the highway pathway delivers a correction at every inference step whose magnitude is independent of depth, in contrast to vanilla PC where the output error reaches the $i$-th hidden layer with attenuation that decays exponentially in depth. This bypasses the Jacobian chain while preserving the local PC synaptic update rule. On MNIST and Fashion-MNIST, we show that HEP effectively trains MLPs of up to 128 layers with accuracy that is robust with respect to depth. --- ### GRADE: Graph Representation of LLM Agent Dependency and Execution Authors: Yue Zhao Published: 2026-06-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.22741v2 A trace records what an LLM agent did at each step. What is gained by also recording what each step relied on? GRADE represents a run as one typed graph: execution edges come free from the trace, and dependency edges are supplied, each graded observed, declared, or inferred. On six observed-dependency corpora spanning tool use, coding, and the web, we price the dependency layer against run size under a fixed logistic probe. Within corpus the layer adds failure-prediction signal on three corpora, though one increment disappears under task-grouped folds and another reverses under a cubic spline. In leave-one-corpus-out transfer the size-normalized dependency block stays above chance on every held-out corpus while run size inverts on two. That pattern belongs to the probe: under a cubic spline the same block falls below chance on four of the six. A preregistered control then holds the node set, the step order and the edge count fixed and varies only which earlier step each dependency edge attaches to. Within corpus it separates the recovered assignment from a degree-matched counterfeit on no corpus, with a six-corpus mean difference of -0.0003. In transfer, scored on the size-plus-dependency arm, only SWE-Gym clears Holm in the six-corpus attachment screen. SWE-Gym, tau-bench and web clear Holm in the separate six-corpus paired task bootstrap. The counterfeit scores higher on two corpora. Withholding each target's whole task family instead leaves no attachment-screen survivor among five targets and turns SWE-Gym's contrast negative at -0.036. Reuse the protocol: grade each edge, keep a run-size baseline, and score matched attachment controls before crediting structure. --- ### GRADE: Graph Representation of LLM Agent Dependency and Execution Authors: Yue Zhao Published: 2026-06-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.22741v1 Can one graph represent every kind of LLM agent's run? A trace records what each step did, never what it relied on, the state it read, and the results it reused. GRADE recovers that missing layer: it models any run as one graph over its step nodes with two edge layers, execution edges (what ran in what order) read from the trace for free, and dependency edges (what each step relied on) rarely logged, so each is graded by how it is known, observed, declared, or inferred. One representation, and each layer earns its place. Across six corpora of LLM agents spanning tool use, coding, and the web, the dependency layer can predict failure where run size is weak and, under leave-one-corpus-out transfer, stays above chance on every held-out class while run size fails. Meanwhile, the execution layer localizes the faulting step in a failed multi-agent run. This work also provides a more in-depth analysis of why generic graph neural networks may misread the dependency layer, unlike our feature-based alternative. The same graph representation opens further uses, carrying from failure diagnosis in a single run to efficiency and robustness optimization at scale. --- ### GroundEval: A Deterministic Replacement for LLM-as-Judge in Stateful Agent Evaluation Authors: Jeffrey Flynt Published: 2026-06-22 Categories: cs.AI, cs.CL, cs.SE arXiv: https://arxiv.org/abs/2606.22737v2 Before letting an agent operate over real context, can you prove it used the right evidence? GroundEval turns that question into a deterministic test of what the agent searched, fetched, cited, and was permitted to access. In one case study, two frontier LLM judges scored a plausible agent response 0.85 and higher. But the trace told a different story: the agent had never retrieved the artifact its answer depended on, yielding a GroundEval score of 0.000. We introduce GroundEval, a judge-free framework for evaluating agents against grounded, time-bounded, and access-controlled evidence. GroundEval uses a domain configuration to generate questions, lets the agent choose how to answer, and then scores both the final answer and the recorded trajectory that produced it. The benchmark targets three failures that LLM-as-judge evaluation struggles to detect: whether an agent checked before claiming absence, reasoned only from evidence available to the actor at the relevant time, and used the correct causal mechanism rather than a plausible one. These correspond to three tracks: Silence, Perspective, and Counterfactual. GroundEval exposes when plausible answers rest on invalid evidence paths, and produces structured per-question diagnostics that pair tool activity with the agent's turn-level narration, making each score inspectable rather than merely reported. Our case studies suggest this failure mode is common rather than exceptional, one that final-answer and judge-based evaluation cannot detect by construction. --- ### Closed-loop Auto Research for Molecular Property Prediction: Discovering and Certifying Generalizable Improvements Authors: Jingjie Ning, Xiaochuan Li, Ji Zeng, Chenyan Xiong, Guolin Ke Published: 2026-06-22 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2606.22731v1 Closed-loop Auto Research extends automated machine learning from fixed-dataset fitting to changing the research workflow, with language-model agents editing representations and model code and acquiring external evidence. Molecular property prediction spans many small endpoints. We ask whether this action space yields improvements generalizing beyond the validation signal selecting them. We isolate three Auto Research axes, features, models, and external evidence, under a file-level ablation lock attributing each gain to one axis over a strong baseline. Across 36 endpoints in three benchmark suites we score each selected configuration once on a held-out test whose labels the search never read. A routed pipeline taking each endpoint's best validation axis reaches positive held-out gains of 0.013, 0.011, and 0.042, the transferable axis differing by suite, data on TDC, model on Polaris, feature and model on MoleculeNet. The largest model-search gain falls from 0.041 on validation to 0.003 on test, while curated data reaches 0.022 but negative 0.019 on test, two non-transfer signatures. Curated external data raises held-out CYP2C9-substrate performance by 0.17 and half-life by 0.08, admitted through a contamination filter rejecting same-source files overlapping 64 to 89 percent of test structures, necessary but not sufficient for transfer. A matched-trial automated machine learning control did not reproduce the agent's code-level model intervention, reaching 0.006 against 0.042, and the pipeline stays competitive with an 84M-parameter pretrained 3D model on the shared training split. The experiments stay within molecular property prediction, but separating discovery from held-out certification is a domain-agnostic lesson for any closed-loop system optimising a proxy for a held-out quantity. --- ### When Confidence Takes the Wrong Path: Diagnosing Retrieval-State Lock-In in RAG Authors: Sahib Julka Published: 2026-06-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.22728v1 The trustworthiness of a retrieval-augmented generation (RAG) system depends on more than the answer it returns, yet many black-box uncertainty methods still read agreement among sampled answers as confidence. That inference fails when repeated samples condition on the same defective retrieval state. The state may be empty, with the model falling back on parametric memory, or populated by a coherent but wrong neighbourhood. In either case, the answers agree because the error is stable. The problem is recognised in deployed RAG, but it has lacked a name, a measurable signature, and a prevalence bound. We supply all three. We name the failure retrieval-state lock-in and diagnose it by separating the three objects a single confidence score conflates: the answer surface, the retrieved evidence, and the retrieval state itself. In an inspectable, ontology-guided knowledge-graph RAG (KG-RAG) system across six question-answering snapshots, we measure the agreement blind spot directly: at five samples per question, 42% of KG-RAG errors and 59% of dense-retrieval errors carry zero answer dispersion, so agreement has nothing to rank, while evidence- and retrieval-state checks still flag most of them. The decomposition supports an auditable decision rule: accepting an answer only when answer, evidence, and retrieval checks all agree that it is low-risk reaches 91.9% pooled precision against a 69.7% accept-all rate. The cost is coverage: it certifies only 7.7% of answers as low-risk. On the clinical calibration domain it reaches 100% precision under an automated judge; this is an in-domain automated-label upper bound, not a clinical safety claim, and still needs human validation. Confidence in RAG is object-specific: when answers agree, the useful question is which part of the pipeline to distrust. --- ### Text Dictates, Music Decorates: Energy-based Attention for Editable Dance Motion Generation Authors: Seong Jong Yoo, Siyuan Peng, Felix Gu, Stratis Aloimonos, Cornelia Fermüller Published: 2026-06-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.22726v2 Choreographic motion generation poses unique challenges for AI, demanding precise semantic control over complex, temporally structured, and expressive full-body dynamics. While existing models can synthesize motion from music, they remain largely black boxes. Conversely, attempting to condition generation on both text and music frequently leads to modality collapse, where dense acoustic rhythms overwhelm sparse semantic text prompts, destroying user controllability. To resolve this spatial-temporal conflict, we propose STREAM (Structural-Temporal Rhythmic Energy-based Attention for Motion), a modality-decoupled diffusion transformer. STREAM strictly separates conditioning pathways: global text semantics dictate the kinematic structure via Adaptive Layer Normalization (AdaLN), while a novel Bimodal Energy-Based Attention Module (BEAM) routes these features to the musical beat without overwriting the semantics. We further introduce Motorica++, a newly curated dataset enriched with domain-specific dance vocabulary and frame-level semantic annotations from existing Motorica dataset. Additionally, to rigorously quantify zero-shot editability, we propose the Exchange Evaluation Protocol and Editable Dance Score (EDS). Through extensive experiments, STREAM achieves state-of-the-art alignment between motion and music while perfectly preserving choreographic semantics, positioning AI not merely as a reactive synthesizer, but as a controllable, collaborative partner for artistic direction. The source code and datasets are available at https://github.com/SeongJong-Yoo/STREAM. --- ### The Race between Agentic AI Capabilities and Data Quality Control in Online Surveys Authors: Sourav Panda, Hillmer Chona, Rupak Kumar Das, Shreyash Kale, Shikha Soneji, Jonathan Dodge Published: 2026-06-21 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.28597v1 Online surveys are a foundational data collection instrument in a variety of fields, with attention checks serving as critical guardians of response quality. However, the rapid emergence of agentic AI (goal directed systems powered by a large language model (LLM) brain and/or a multimodal processing unit with tool-augmented capabilities) raises new questions about the robustness of these safeguards. We investigate how well agentic AI architectures can complete web-based surveys and pass standard attention checks. We evaluate a single-agent architecture capable of multimodal input processing and tool-based web interaction on a controlled survey sandbox. We analyze the problem from two perspectives. From an attack perspective, we demonstrate how structural vulnerabilities such as exposed DOM metadata and predictable option encoding allow agents to resolve attention checks through structured parsing only. From a defense perspective, we implement a mitigation strategy of DOM metadata obfuscation to remove semantic cues in text-based questions. We evaluate multiple open-source language and multimodal models to study capability and orchestration effectiveness. Based on our evaluations, we offer perspectives on how to simultaneously meet the needs of empiricists and agentic AI researchers. --- ### Which India Survives Translation? Narrative Homogenisation Across Indian Oral Traditions in LLMs Authors: Paarth Singh Rathore Published: 2026-06-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.26123v2 Large language models (LLMs) are trained predominantly on English-language internet text that over-represents certain cultural narratives, raising concerns that models flatten the diversity of non-Western storytelling traditions into a single homogenized archetype. We present a pilot computational study examining this across three maximally distinct Indian regional oral and literary traditions: the Rajasthani Pabuji epic, classical Tamil Sangam poetry, and Bengali folk tales. We collected authentic reference corpora for each tradition (11, 21, and 10 passages respectively) and prompted two LLMs (Claude Sonnet and Gemini) with 54 generation requests spanning three prompt types per tradition - generic, culturally specific, and regional-language. Using Sentence-BERT embeddings and cosine similarity, we measure reference drift (how closely outputs track their own tradition's authentic texts relative to the other two) and cross-tradition convergence (how similar outputs are across traditions). We find that while outputs remain closer to their own tradition's reference than to others, cross-tradition similarity is high (0.52-0.66) relative to what the traditions' genuine distance would predict, indicating partial homogenisation. Unexpectedly, prompting in the regional language (Hindi, Tamil, or Bengali) consistently reduced fidelity to the authentic tradition relative to English prompting, by as much as 27 percentage points for Rajasthani and Bengali traditions. We discuss this against conflicting prior results on multilingual prompting and argue it reflects a difference between eliciting general cultural diversity and simulating one narrow, lesser-documented oral tradition. We position this pilot as a lightweight, scalable complement to recent large-scale human-annotation studies of Indian cultural misrepresentation in LLM-generated stories, as part of a broader doctoral research program. --- ### Wazobia Eval: A Benchmark for Nigerian Pidgin Emotion Understanding, Sarcasm Detection, and Cultural Reasoning Authors: Stephanie Okoye Published: 2026-06-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.21369v1 Nigerian Pidgin is one of Africa's most widely spoken languages, yet remains severely underrepresented in language model evaluation. Existing benchmarks primarily focus on translation, transcription, or generic sentiment analysis, leaving critical aspects of culturally grounded language understanding unmeasured. We introduce Wazobia Eval, a benchmark for evaluating Nigerian Pidgin emotion understanding, sarcasm detection, and cultural reasoning. The benchmark is built on a manually annotated dataset containing over 550 examples and a 16-category emotion taxonomy designed to capture culturally specific emotional registers that are not represented in conventional sentiment frameworks. Wazobia Eval provides standardized evaluation protocols and benchmark tasks for assessing model performance on nuanced Nigerian language understanding. We present the benchmark design, annotation methodology, taxonomy development process, and preliminary pilot evaluation results. Our goal is to provide foundational evaluation infrastructure for Nigerian language AI and establish a reproducible benchmark for future research. The dataset is publicly available at https://huggingface.co/WAZOBIALABS. --- ### The Multilingual Quantization Tax: Structural Collapse and Typological Fragility in Edge SLMs Authors: Mohammad Wathiq Soualhi Published: 2026-06-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.09941v1 While 4-bit weight quantization is critical for deploying Small Language Models (SLMs) on edge devices, evaluations of the resulting performance degradation-the quantization tax-remain overwhelmingly English-centric. We present a zero-shot multilingual evaluation of 4-bit quantization across the Gemma 4 and Qwen 3.5 architectures. Evaluating on eight typo-logically diverse languages using MMLU ProX Lite and GlobalPIQA, we show parameter truncation exposes deep pre-training inequalities. We identify four phenomena: (1) Typological Fragility: low-resource and specific non-Latin scripts suffer representational collapse via architecture-specific double dissociations, failing to generate valid task logits; (2) Home Language Fragility Paradox: foundational pre-training pathways provide limited precision loss protection; (3) Domain-Specific Forgetting: multi-step cross-lingual routing degrades while associative soft-science recall remains robust; and (4) Quantization Resistance: highly saturated, typologically aligned domains resist deterministic degradation, with post-quantization performance gains bounded by statistical noise. --- ### Do Methods Support the Claims? Intra-Paper Verification for Peer Review Authors: Ranjitha Shivaprasad Ballakuraya, Arash Mahyari, Ashok Srinivasan Published: 2026-06-21 Categories: cs.CL, cs.AI, cs.DL arXiv: https://arxiv.org/abs/2607.26066v1 The growing volume of scientific submissions has motivated interest in using large language models (LLMs) to assist peer review. Existing automated novelty assessment approaches typically compare a paper's claimed contributions against prior literature, implicitly assuming that these contributions are accurately realized in the work itself. Human reviewers, however, frequently challenge novelty claims not because similar ideas already exist, but because the methodological evidence presented in the paper does not adequately support them. This internal mismatch between claimed contributions and methodological realization is rarely examined by current LLM-based review systems. To address this gap, we introduce intra-paper claim verification, a framework that evaluates whether novelty claims articulated in a paper are substantiated by the methods used to realize them. The framework employs an LLM to extract novelty claims from the introduction, retrieve claim-relevant methodological evidence, and assess whether the methods substantiate the stated contributions. Assessment is guided by reviewer-inspired evaluation criteria derived inductively from human peer reviews collected from 182 ICLR 2025 papers. These criteria capture recurring reviewer concerns related to novelty, methodology, clarity, and other issues and are used to generate structured reviewer-style assessments of claim substantiation. We evaluate the framework by comparing LLM-generated review comments against human reviewer concerns on a balanced subset of accepted and rejected papers. Human evaluation demonstrates significant alignment between framework-generated assessments and human reviewer concerns, particularly for novelty-related issues. BERTScore further distinguishes corresponding human-LLM review pairs from mismatched controls, indicating that the framework captures concerns consistent with human reviewer observations. --- ### Personalization, Personas, and Forecasting in Value Alignment Authors: James Wedgwood, Pratiksha Thaker, Neil Kale, Virginia Smith Published: 2026-06-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.24782v1 LLM behavior may be conditioned by human identity in several ways: they may be asked to adapt to users, role-play populations, or forecast how people would answer value-laden questions. We test whether these framings are interchangeable using the World Values Survey (WVS). We evaluate GPT-5.4, Claude Sonnet 4.6, Gemini 2.5 Flash, and Qwen3-235B on 101 WVS-derived questions across 13 language-country slices, comparing a language-only baseline with user-country, persona-country, and third-person prompts. Across 21,008 model-response rows, prompt framing is a first-order determinant of cultural alignment: country cues often shift answers substantially, but not all shifts move toward matched human response distributions. Third-person forecasting yields the strongest directional alignment for three of the four hosted models, while personalization and role-play are weaker or less stable. Alignment gains concentrate on salient value dimensions such as religiosity, gender roles, and work-oriented material values, whereas institutional trust and democracy-related questions remain difficult. These results show that prompt framing is not a cosmetic choice in cultural value elicitation; it changes both model behavior and measured alignment. --- ### Physics-Informed Domain-Invariant Feature Learning with Autoencoder-Driven Gaussian Clustering for Robust Non-line-of-Sight Scenarios Authors: Nisha L. Raichur, Lucas Heublein, Dominik Seuß, Frank Deinzer, Felix Ott Published: 2026-06-21 Categories: eess.SP, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2607.02537v1 Jamming and spoofing pose significant threats to wireless and satellite navigation by disrupting radio-frequency (RF) signals and compromising availability and integrity. Robust RF interference direction finding through angle-of-arrival (AoA) estimation is therefore essential for detecting and localizing anomalous signals. Although data-driven methods perform well under line-of-sight (LoS) conditions, their performance degrades in practical environments due to non-line-of-sight (NLoS) multipath propagation. In this work, we propose a hybrid learning framework that incorporates physics-informed constraints into deep neural networks to improve the robustness of AoA estimation. A neural network is trained to estimate the azimuth and elevation of incoming signals received by a four-element antenna array, while a physics-informed loss enforces consistency between the predicted angles and inter-antenna phase differences under a plane-wave model. We further introduce a latent-space classifier to distinguish LoS from NLoS samples. Since inter-antenna phase differences under LoS propagation exhibit domain-invariant structure across environments, the physics-based loss is applied only to LoS samples, promoting physically consistent and domain-invariant representations without over-constraining the model in NLoS scenarios. In addition, domain-incremental learning (DIL) across NLoS environments with varying scatterer distributions improves cross-domain generalization. Evaluations on real-world datasets show that the proposed method reduces AoA estimation error by up to 6° in low-exemplar settings compared with DIL baselines. --- ### Urban Deceleration Behavior Modes Under Scene Context: An Early-Kinematic Classifier from Argoverse 2 Multi-Agent Trajectories Authors: Eni Solomon Laughter Published: 2026-06-21 Categories: cs.RO, cs.LG, eess.SP, eess.SY arXiv: https://arxiv.org/abs/2607.00027v1 Urban deceleration is one of the most empirically studied yet least taxonomically organized behaviors in car-following research. Recent perception-equipped autonomous-vehicle datasets enable trajectory-anchored mode discovery. We extract 1,219 sustained deceleration events from 234 urban driving logs of the Argoverse 2 Sensor dataset, encode each event in a 19-dimensional kinematic feature vector, discover behavioral modes via K-means clustering with bootstrap stability analysis, and quantify modulation by eleven scene-context variables. A HistGradientBoosting classifier predicts mode membership from the first 1.0 s of each event. Four stable modes emerge with a bootstrap Adjusted Rand Index of 0.897 across 50 resamples: anticipatory soft (62.8%), reactive closing (30.6%), brake-like jerk (4.8%), and an outlier category (1.8%). Only pair age shows a medium effect (epsilon^2 = 0.085); scene geometry and vulnerable-road-user proximity show negligible effects. The early-event classifier achieves macro-F1 = 0.758 at 1.0 s, with scene context contributing +0.059 F1 over kinematics alone. Modes are regime-invariant in medium-speed driving (ARI = 0.817) but regime-dependent at low speed (ARI = 0.166). A small set of stable kinematic modes structures urban deceleration; early-window jerk dominates predictive signal; and pair age is the primary contextual modulator. --- ### FLYNN: Robust Neural Network for Robot Navigation using Fly Brain Topology Authors: Benquan Wang, Jingdao Chen Published: 2026-06-21 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.00025v2 While deep learning models achieve state-of-the-art performance in complex tasks, they remain brittle when faced with new environments or sensory deprivation. In contrast, biological systems exhibit remarkable tolerance to these challenges. We address this vulnerability by developing a recurrent neural network (RNN) whose architecture is directly derived from the synaptic-resolution brain connectome of the fruit fly Drosophila melanogaster. We demonstrate the feasibility of training the fly connectome neural network (FLYNN) to perform vision-based navigation in MuJoCo, achieving performance comparable to modern hand-crafted networks of similar parameter counts. Crucially, FLYNN exhibits superior resistance to out-of-distribution (OOD) data and tolerance to sensory loss without further training. It remained functional even under total vision loss while hand-crafted networks largely failed, even when specifically trained with camera dropout. Principal Component Analysis (PCA) of the internal state of FLYNN suggests that it exhibits a particularly high degree of representational modularity, which might be related to its robustness. Our work provides a new direction for designing resilient artificial agents following the topology of biological brains. --- ### Emergent Culture in Minimal LLM Systems Authors: Simon Jones, Sabine Hauert Published: 2026-06-21 Categories: cs.NE, cs.AI, cs.CL, cs.MA, nlin.AO, q-bio.PE arXiv: https://arxiv.org/abs/2606.30668v1 What happens when LLM agents operate with no context outside a turn, minimal prompting, and simple tools? Inspired by swarm engineering, we give collectives of three agents the ability to send messages and manipulate a shared actively decaying text store, introducing evolutionary pressure. The agents spontaneously cooperate, develop storage management strategies, and generate complex evolving cultural artifacts, with no top-down engineering. Using tools from dynamical systems analysis, we show that these behaviours exhibit structured long-range coherence beyond the entropy horizon of the decaying store, consistent with emergent culture in the Sperberian sense. --- ### Zero-Label Driving Scenario Complexity Detection via Joint Embedding Predictive Architecture Authors: Santosh Jaiswal Published: 2026-06-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.28383v1 Identifying complex and safety-critical driving scenarios in large unlabelled datasets is an important but expensive problem. Existing approaches rely on human annotators, supervised classifiers, or carefully engineered rule sets, all of which require substantial prior knowledge about what constitutes a difficult scenario. We ask whether a model can discover scenario complexity on its own, with no labels at any stage. We train a minimal Joint Embedding Predictive Architecture (JEPA) on structured agent state data from the nuPlan mini dataset and use the temporal prediction error as a zero-shot complexity score. Without access to any ground-truth labels during training or evaluation setup, the model assigns significantly higher scores to scenarios involving unprotected turns, crosswalk interactions, and pedestrian proximity, and significantly lower scores to lane-following and stationary-traffic scenarios. We validate this finding through four ablation experiments that isolate the source of the signal, and through a downstream anomaly detection evaluation that achieves Average Precision of 0.512 against a 0.436 chance baseline. The results show that temporal prediction error in a self-supervised latent world model is a practical proxy for driving scenario complexity. --- ### Neural Speaker Diarization via Multilingual Training: Evaluation on Low-Resource Nepali-Hindi Speech Authors: Samip Neupane, Sandesh Pokhrel, Sandesh Pyakurel, Basanta Joshi Published: 2026-06-21 Categories: cs.SD, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.26144v1 Speaker diarization, the task of determining "who spoke when" in a multi-speaker recording, is a critical component in applications such as meeting transcription, accessibility tools, and multilingual information retrieval. While end-to-end neural diarization systems have achieved strong performance for English and other high-resource languages, their effectiveness degrades substantially for underrepresented languages where annotated speech data is scarce. This paper investigates speaker diarization for low-resource Nepali-Hindi speech through a multilingual training approach, comparing two modern architectures: EEND with encoder-decoder attractors (EEND-EDA) and EEND with Perceiver-based attractors (DiaPer). Both models are trained on a multilingual corpus combining English speech from LibriSpeech, diverse speaker recordings from VoxCeleb, and separately collected Nepali and Hindi audio, a setup designed to reduce language bias and encourage cross-lingual generalization. We evaluate both models across 2-speaker, 3-speaker, 4-speaker, and mixed-speaker scenarios on LibriSpeech, VoxCeleb, and Nepali-Hindi (NeHi) test sets. DiaPer achieves stronger overall performance than EEND-EDA, particularly in more challenging multi-speaker conditions, obtaining DERs of 3.28%, 2.02%, 4.05%, and 4.76% on NeHi 2-speaker, 3-speaker, 4-speaker, and mixed-speaker settings, respectively, compared to 1.50%, 9.68%, 16.17%, and 11.19% for EEND-EDA. These results demonstrate the viability of Perceiver-based end-to-end neural diarization for low-resource multilingual speech processing. --- ### JEDEL: Zero-Shot DNA-Encoded Library Design for Early-Stage Drug Discovery Authors: Zygimantas Jocys, Zhanxing Zhu, Henriette M. G. Willems, Katayoun Farrahi Published: 2026-06-21 Categories: q-bio.BM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.23745v1 We present JEDEL, a framework for generating synthesis-ready DNA-encoded libraries (DELs) directly from three-dimensional pharmacophore representations of active ligands. JEDEL is the first model to map pharmacophore interaction patterns to actionable, scalable synthesis instructions, enabling the design of targeted libraries comprising potentially millions of molecules. Unlike existing generative approaches that produce virtual compounds requiring downstream synthesis planning, JEDEL operates within the space of purchasable building blocks and validated reactions, ensuring that every output is experimentally realizable by construction. JEDEL learns a predictive alignment between pharmacophore geometry and molecular structure and decodes this into combinatorial synthesis routes at scale. Across 18 protein targets, it generates focused libraries that outperform random and diversity-based baselines in predicted binding affinity, pharmacophore recovery, and sample efficiency, without target-specific retraining. JEDEL enables a shift from virtual molecule generation to experimentally deployable library design. --- ### Performance and Interpretability of Convolutional, Transformer, and Hybrid Deep Learning Models in Colorectal Histology Classification Authors: Reza Bozorgpour Published: 2026-06-21 Categories: q-bio.QM, cs.CV arXiv: https://arxiv.org/abs/2606.23744v1 Deep learning has become an important tool in computational pathology, enabling automated analysis of histopathological images. While convolutional neural networks (CNNs) have traditionally dominated this field, transformer-based and hybrid architectures have recently demonstrated promising performance. However, comprehensive comparisons of these approaches for colorectal histopathology remain limited. This study evaluated twelve ImageNet-pretrained CNN, transformer, and hybrid architectures using the Kather colorectal histopathology dataset containing 5,000 image tiles from eight tissue classes. All models were trained using a standardized transfer-learning and fine-tuning protocol and assessed using multiple performance metrics, including accuracy, precision, sensitivity, specificity, F1-score, ROC-AUC, Cohen's kappa, and Matthews correlation coefficient. All evaluated models achieved high classification performance, with accuracies ranging from 93.2% to 97.1%. EVA-02 achieved the highest overall performance (97.1% accuracy, 97.0% F1-score), closely followed by ViT-B/16. Among CNNs, ResNet34 and ConvNeXt-Tiny demonstrated highly competitive performance, achieving accuracies of 96.4% and 96.3%, respectively. Transformer architectures generally produced the strongest results across evaluation metrics, although the performance gap between the best transformer and CNN models was relatively small. Per-class analysis showed consistently strong classification performance across all tissue categories, with Complex Stroma representing the most challenging class. Overall, transformer-based architectures achieved the highest predictive performance, whereas modern CNNs provided a favorable balance between accuracy and model complexity. These findings provide a comprehensive benchmark of major deep learning paradigms for colorectal histopathology classification. --- ### Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation Authors: Yitong Li, Junsong Chen, Haopeng Li, Haozhe Liu, Jincheng Yu, Ligeng Zhu, Ping Luo, Song Han, Enze Xie Published: 2026-06-21 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.23743v2 Modern video diffusion models achieve higher generation quality through scaling, but this also increases inference cost. Although many acceleration methods have been proposed, a central challenge is that the most effective acceleration strategy is highly instance-specific: a recipe that works well for one combination of model, hardware, and inference configuration often does not transfer to another. Different models vary in architecture, numerical sensitivity, and attention concentration patterns. Inference settings differ in spatial and temporal resolution and video duration, while hardware platforms differ in memory hierarchy, supported numerical formats, and kernel throughput. These factors create a large tuning space, making manual performance engineering costly. We present Sol Video Inference Engine, an agentic, native, training-free acceleration framework for video diffusion models. It organizes five broadly applicable techniques, cache, sparse attention, token pruning, quantization, and kernel fusion, into an agentic acceleration stack for instance-specific optimization. For a concrete deployment target defined by a model, hardware platform, and serving configuration, parallel skill agents optimize the implementation of each technique, an agent integrator composes them into a global acceleration stack, and a human validator provides feedback on generation quality. We instantiate this workflow on three video models with different sizes and architectures: 64B Cosmos3-Super, 22B LTX-2.3, and 2B SANA-Video. With little human effort, the full stack achieves more than 2x end-to-end acceleration while maintaining near-lossless VBench quality, demonstrating the effectiveness of the agent framework for video diffusion acceleration. --- ### Low-power analogue neural networks with trainable nonlinear connections for continuous control Authors: Ian T. Vidamour, Fernando Aguirre, Thomas J. Hayward, Matthew O. A. Ellis, Charles Swindells, Alexander McDonnell, Martin Trefzer, Finley Robins, Luca Manneschi, Susan Stepney, Tony Kenyon, Oliver J. Sutton et al. Published: 2026-06-21 Categories: cs.LG, cs.AI, cs.AR arXiv: https://arxiv.org/abs/2606.23742v1 Physical neural networks promise low-power machine learning by computing directly with analogue device physics, but most architectures force nonlinear device responses to act as scalar weights. Inspired by Kolmogorov-Arnold networks, we place trainable nonlinear functions on the connections, making each physical connection a learnable computational element. Realising these functions as analogue band-pass filters on field-programmable analogue arrays, we find that the benefit is task-dependent and follows from the smoothness of the physical basis: the networks represent smooth, continuously valued targets, including robotic kinematics, continuous control, and photovoltaic maximum-power-point tracking, with far fewer nodes and connections than multilayer perceptrons, but offer no parameter-efficiency advantage on classification-like decision boundaries. Trained networks transfer to hardware across approximately 35,000 connections with quantified fidelity, and a dedicated CMOS implementation is projected to operate at approximately 30 microwatts. A memristive realisation reproduces the same behaviour in simulation, indicating that the advantage comes from placing trainable nonlinearity on connections, rather than from a particular device. --- ### A Survey on Federated Causal Discovery and Inference Authors: Xianjie Guo, Yuwei Wang, Guodu Xiang, Xiaoli Tang, Kui Yu, Han Yu, Qiang Yang Published: 2026-06-21 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2606.23741v1 Causal reasoning, which encompasses the discovery of causal structures and the inference of causal effects, is fundamental to data-driven decision making. In practice, data for reliable causal analysis are often distributed across institutions and cannot be centralized due to privacy regulations or communication constraints. Federated learning (FL) addresses this by enabling collaborative analysis without raw data sharing, giving rise to the rapidly growing field of federated causal discovery (FCD) and inference (FCI). However, the interdisciplinary nature of this field and the absence of a comprehensive survey present barriers to entry for researchers. This paper bridges that gap by providing a systematic review through multi-dimensional taxonomies. Grounded in the three core design decisions underlying any FCD solution, namely how structures are learned, how data are partitioned, and what structural knowledge each party obtains, we organize FCD along three axes: methodological paradigm, federation topology, and structural scope. We further examine key practical dimensions, including temporal dynamics, data heterogeneity, missing data, and non-identical variable sets. For FCI, we categorize methods by target estimand (average versus individualized/conditional treatment effects) and by estimation strategy, from classical weighting methods to modern deep generative architectures. Unlike prior works that treat FCD and FCI separately, we formalize their connection as complementary stages of a unified federated causal reasoning pipeline, where FCD supplies the structural knowledge required for valid effect estimation in FCI. Finally, we highlight their shared concerns regarding privacy, communication efficiency, theoretical guarantees, and application domains, and conclude by identifying open challenges for future research. --- ### Weight-Space Geometry of Offline Reasoning Training Authors: Aleksandr Nikolich, Igor Kiselev, Vladimir Platonov, Karina Romanova Published: 2026-06-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.23740v1 Offline reinforcement-learning losses (RFT, RIFT, DFT, Offline GRPO, DPO) are widely used to distill reasoning from large teachers into smaller students, and are typically compared on downstream accuracy alone. We ask whether they are mechanistically distinct or converge to a similar weight update. Training six methods (SFT, RFT, DFT, RIFT, Offline GRPO, DPO) on identical math rollouts from a single base model (Qwen3-4B) with attention-only LoRA, we analyze the resulting deltas via cosine similarity, principal-angle subspace analysis, linear mode connectivity, and CKA. We observe: (i) SFT, RFT, and RIFT have nearly colinear weight deltas (cosine >= 0.97, top-1 principal angle ~7 deg median over 144 modules) and comparable GSM8K accuracy (87-88%, n=1319; pairwise McNemar p >= 0.15); (ii) DFT diverges further in direction than any reward-weighted method despite using the same data; (iii) Offline GRPO adds a substantial component orthogonal to the SFT direction (~67% globally, up to ~86% in late layers) while staying in the SFT loss basin; (iv) DPO sits in a near-orthogonal subspace, shows a mode-connectivity barrier, and collapses late-layer CKA to ~0.46. DPO also reaches the highest accuracy in our protocol on both GSM8K (93.5%, McNemar p < 10^-9 vs. each other method) and AIME26 (30.0% vs. 3.3-10.0%); its training uses a 10x smaller learning rate than the others (the standard convention), so the update-norm and accuracy gaps reflect loss-function and optimizer choices jointly, and a learning-rate-matched DPO comparison is left for future work. --- ### Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search Authors: Yashkumar R Lukhi, Harsh Rameshbhai Moradiya, Radu Timofte, Dmitry Ignatov Published: 2026-06-21 Categories: cs.LG, cs.CV, cs.SE arXiv: https://arxiv.org/abs/2606.23739v1 We present an automated large-scale search pipeline for heterogeneous 4-Expert Mixture-of-Experts (MoE4) architectures within the LEMUR neural network dataset ecosystem. Building on a hand-crafted heterogeneous MoE reference model, we replace manual design with a deterministic code-assembly generator that systematically combines base architecture families drawn from the LEMUR database into MoE4 ensembles, each governed by a convolutional gating network with temperature scaling, mixup augmentation, and cosine-annealed learning rate scheduling. Over a 28-day campaign on an NVIDIA RTX 4090, the pipeline generated 4,463 candidate models across 197 batches, of which 1,021 were evaluated successfully. A critical finding emerged from the campaign: due to alphabetical enumeration via itertools.combinations, the entire explored search space (4.8% of the theoretical 23,751 possible 4-family combinations) is anchored to a single family, AirNet. We characterise this coverage bias precisely, identify the root cause in the generator, and propose a stratified random sampling fix. Within the AirNet anchored scope, ShuffleNet and MobileNetV3 consistently co-produce the highest-accuracy ensembles (mean accuracy up to 0.632), while FractalNet and MNASNet are identified as low-yield families warranting exclusion in future campaigns. The pipeline, analysis artefacts, and corrected generator are released as part of the open-source NNGPT project at https://github.com/ABrain-One/nn-gpt --- ### Interpretable Uncertainty Routing Separating Emotion Ambiguity from Distribution Shift in Facial Expression Recognition Authors: Keito Inoshita, Takato Ueno Published: 2026-06-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.22725v1 Facial expression recognition (FER) is inherently ambiguous: human annotators frequently disagree, and models deployed in real environments face distribution shift. Crucially, these two conditions demand different downstream actions, as ambiguous in-distribution faces should be reported with their ambiguity whereas out-of-distribution inputs should be rejected. However, a single uncertainty score conflates the two. In this study, uncertainty decomposition into aleatoric and epistemic components for FER is investigated, and Uncertainty-Aware Routing (UAR), an inference-time routing mechanism that exploits the separation, is introduced. Specifically, aleatoric and epistemic uncertainties are obtained from a Deep Ensemble of fully fine-tuned DINOv2 models and are each validated against an independent external signal: aleatoric against human annotator disagreement, and epistemic against distribution shift induced by image corruptions. The proposed dual-validation protocol reveals that aleatoric recovers annotator disagreement with Spearman correlation 0.66 (95% CI: 0.64-0.68), and epistemic detects corruption-induced shifts, achieving average AUROC of 0.699 at the highest corruption severity. UAR retains approximately 1.8 times more ambiguous in-distribution faces than single-uncertainty routing at a matched out-of-distribution rejection rate. A strong label-distribution-learning baseline achieves comparable disagreement recovery but cannot separate ambiguity from shift and therefore cannot route, establishing that the value of decomposition lies in the separation enabling interpretable and differentiated action selection. --- ### Subspace-Constrained Federated Learning with Low-Rank Adaptation Authors: Neranjan Senarath, Rohit Muralitharan, Sadia Asif Published: 2026-06-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.22724v1 Federated low-rank adaptation methods are attractive for fine-tuning large models under communication and privacy constraints, but heterogeneous client data can induce geometric misalignment between local low-rank updates. We study whether this subspace misalignment leads to destructive aggregation and slower convergence in LoRA-based federated learning. We propose a subspace-regularized federated LoRA objective that encourages local client updates to remain close to a shared global reference subspace. We present a complete empirical evaluation on two pretrained models, RoBERTa-large and SmolLM-360M, over HellaSwag in a non-IID 10-client federated setting, across 3 random seeds (42, 43, 44), yielding 24 total experimental runs (4 methods x 3 seeds x 2 models). On RoBERTa-large, Subspace-Reg achieves the strongest mean best accuracy (0.454 +/- 0.023), mean final accuracy (0.429 +/- 0.011), and lowest final loss (1.363) across all three seeds, outperforming FedAvg, SVD redistribution, and FedSVD baselines by a large margin. On SmolLM-360M, FedAvg leads on accuracy, revealing that accuracy gains are model-dependent. Crucially, Subspace-Reg achieves near-perfect basis overlap, approximately 0.9999, on both models and across all seeds, versus 0.958 to 0.991 for all baselines, providing robust support for the geometric alignment hypothesis. The code is publicly available at https://github.com/sadia-sigma-lab/Subspace-Constrained-Federated-learning-with-Lora. --- ### BLUEX v2: Benchmarking LLMs on Open-Ended Questions from Brazilian University Entrance Exams Authors: João Guilherme Alves Santos, Giovana Kerche Bonás, Thiago Laitz, Thales Sales Almeida, Helio Pedrini Published: 2026-06-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.22723v2 Although Large Language Models (LLMs) excel in many tasks, their assessment in Portuguese has received less attention, particularly for open-ended, discursive tasks that demand deeper reasoning and generation capabilities. While the original BLUEX benchmark addressed the scarcity of Portuguese evaluation datasets through multiple-choice questions from Brazilian university entrance exams, it did not cover the more challenging second-phase examinations, which require free-form written responses. In this work, we introduce BLUEX v2, a benchmark derived from the second-phase entrance exams of Brazil's two leading universities: UNICAMP (Comvest) and USP (Fuvest), spanning exam years 2022--2025. Our dataset comprises 395 questions unfolding into 919 graded subquestions, with 55.7% of questions containing associated images (represented as context-aware captions during inference to enable evaluation across both vision-capable and text-only models). Each question is annotated with subject area, official reference answers, LLM-generated rubric criteria, and six cognitive capability tags. We evaluate 21 state-of-the-art LLMs using an LLM-as-a-judge protocol. Results reveal a 4.92-point performance spread across models (4.18-9.10 on a 0-10 scale), with Mathematical Reasoning and Image Understanding emerging as the hardest capability dimensions. The evaluation code, model outputs, and dataset are publicly available at https://github.com/TropicAI-Research/BLUEXv2 and on Hugging Face at https://huggingface.co/datasets/Tropic-AI/BLUEX-v2. --- ### moBERTo: A Modern Encoder for Portuguese via Continued Pretraining of ModernBERT Authors: Thiago Laitz, Thales Sales Almeida, João Guilherme Alves Santos, Giovana Kerche Bonás Published: 2026-06-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.22722v1 Encoder-only transformer models remain essential for production NLP pipelines. We introduce moBERTo, a Portuguese adaptation of ModernBERT obtained through continued pretraining of the ModernBERT-base checkpoint on 60 billion tokens (5 epochs over a 12-billion-token corpus curated from FineWeb2 and filtered with educational and STEM classifiers). We preserve the original architecture, including rotary positional embeddings, alternating local-global attention, flash attention, and unpadding. We evaluate moBERTo across information retrieval (including long-context retrieval at up to 8,192 tokens), document classification, named entity recognition, and natural language understanding. Our best variant, which combines a Portuguese tokenizer with subword-matching embedding transfer and long-context post-training, achieves the highest average reranking nDCG@10 across three Portuguese retrieval benchmarks and the best results on PLUE-PT. Through ablation studies, we show that (i) continued pretraining is strongly preferable to training from scratch, particularly for preserving long-context capabilities; (ii) tokenizer adaptation improves token-level tasks but degrades long-context retrieval; (iii) a dedicated long-context post-training phase at 8,192 tokens further improves reranking and NER; and (iv) encoder-only architectures remain competitive with larger decoder-only alternatives for discriminative tasks. We publicly release the model weights at https://huggingface.co/Tropic-AI/moBERTo and training data at https://huggingface.co/datasets/Tropic-AI/moberto-pretraining-dataset-c4-compatible on Hugging Face. --- ### Leakage-Aware Benchmarking of LLM Forecasting: Real-Time Nowcasts as the Decision-Time Input for Macro Factor Ranking Authors: Mao Guan, Qian Chen Published: 2026-06-21 Categories: q-fin.ST, cs.AI arXiv: https://arxiv.org/abs/2606.22719v1 Forecasting benchmarks for retrieval-augmented LLMs routinely confound model capability with information leakage: features labeled with a target's timestamp are often not observable at the system's decision time. We study leakage-controlled equity factor ranking with a retrieval-augmented 7B open-source LLM forecaster. At each month-end from 2023-04 to 2026-03, the forecaster observes only decision-time information: lag-shifted FRED macro variables, recent macro-event summaries, and the Cleveland Fed's archived daily CPI nowcast for unreleased current-month inflation. A macro-analog retrieval module selects historical states, a critic LLM compresses them into one tactical rule, and an actor LLM maps the current state and recent rules into scores for seven U.S. equity style factors. The full pipeline obtains a median monthly Spearman rank IC of +0.154, with positive means across three non-overlapping contiguous 12-month subwindows; the mean IC remains statistically underpowered, with a bootstrap 95% confidence interval that includes zero. Non-LLM baselines under the same decision-time constraint demonstrate that a kNN macro-analog model recovers a comparable median IC, indicating that real-time inflation information and macro-similar retrieval explain much of the median signal. The LLM pipeline retains higher mean IC and a stronger long-short allocation sanity check, suggesting that any marginal benefit is concentrated in the extreme rankings that drive long-short portfolio formation. A descriptive audit of the 36 critic rules and per-month case studies appears in the appendix. --- ### Generative Relightable Avatars Authors: Kunwar Maheep Singh, Christian Theobalt, Rishabh Dabral Published: 2026-06-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.22718v2 We present Generative Relightable Avatars (GRA), a person-specific method for photorealistic free-view rendering and environment-map relighting of full-body humans. We postulate that modeling fine-grained appearance details is inherently a one-to-many problem that can benefit from a generative formulation. In contrast to fully regressive relightable avatar methods, GRA follows a hybrid approach that combines controllable, physics-grounded relighting with probabilistic refinement. Starting from a tracked animated mesh, we optimize material parameters in UV-space and render a coarse relit appearance under a target HDR environment map. Next, we refine the textures with a feed-forward model to capture pose-dependent texture dynamics and illumination effects beyond simplified reflectance assumptions. Finally, a fine-tuned video-to-video diffusion model transforms the physically grounded renderings into temporally coherent, high-detail videos while preserving 3D control, with an error-recycling strategy for generating long videos. Experimental evaluations demonstrate our method's improved perceptual quality over prior relightable avatar baselines. Project Page: https://vcai.mpi-inf.mpg.de/projects/GRA/ --- ### Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards Authors: Jungseob Lee, Seungyoon Lee, Seongtae Hong, Minhyuk Kim, Chanjun Park, Heuiseok Lim Published: 2026-06-21 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.22716v1 Training large language models to reason efficiently is a critical challenge. While integrating length-penalizing rewards into Group Relative Policy Optimization (GRPO) aims to reduce verbosity, it frequently triggers reward collapse, severely degrading reasoning capabilities. Through a systematic evaluation of various reward configurations, we identify the root mechanism: GRPO's group normalization creates divergent advantages when incorrect answers receive continuous length penalties. Consequently, methods penalizing the length of incorrect answers are structurally prone to collapse under sustained optimization. Furthermore, restricting penalties exclusively to correct answers avoids this primary failure, but leaves the model susceptible to a stochastic collapse driven by response over-compression. To robustly prevent both failure modes, we propose ACOER (Adaptive Correct-Only Efficiency Reward). ACOER eliminates the structural penalty loop by isolating brevity bonuses to correct completions and prevents stochastic compression via dynamic budget normalization and control-loop penalty adjustments. Evaluated across diverse mathematical reasoning benchmarks, ACOER improves overall accuracy compared to the base model while reducing token generation by over 60%, establishing a fundamentally stable approach for efficiency-aware optimization. --- ### Beyond Simpson's Paradox: A Cascade of Confounders in AI Agent Pull-Request Co-Authorship Authors: Haoran Yu, Xiaochong Jiang, Lifei Liu, Su Wang, Pin Qian, Yihang Chen Published: 2026-06-21 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2606.22711v1 Pooled across five AI coding agents, pull requests (PRs) with a human Co-Authored-By trailer merge less often than purely-autonomous ones (53.8% vs. 79.8%) -- yet this aggregate finding is a textbook Simpson's Paradox. Stratifying 33,596 PRs from the AIDev dataset by agent identity reverses the conclusion: Copilot and Devin show large positive within-agent gaps (+41.2 and +33.5 pp, both p<0.001), while Cursor, Claude Code, and Codex show small effects whose cross-sectional 95% CIs span zero. The paradox is driven entirely by agent composition: Codex, which dominates 64.9% of the dataset, achieves high merge rates while rarely using co-authorship. But Simpson's Paradox is only the first layer of a cascade of confounders: within-repo controls eliminate Devin's gap (+33.5 to +1.6 pp, p=0.73); a commit-count control further halves Copilot's within-repo gap (+36.2 to +24.4 pp); restricted to multi-commit PRs, the Copilot within-repo effect dissolves to +4.8 pp (p=0.59). No agent retains a clear co-authorship effect once both repository selection and PR structure are controlled. Our findings caution against reporting agent-pooled statistics without stratification and demonstrate that cross-sectional co-authorship associations are largely selection and PR-structure artefacts rather than evidence of a causal benefit. --- ### Libretto: Giving LLM Agents a Sense of Musical Structure Authors: Yichen Xu Published: 2026-06-21 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2606.22708v1 Generative music systems can now produce impressive audio from text prompts, but audio outputs are difficult to inspect, edit, and diagnose as musical structure. We introduce Libretto, an agent-facing framework for symbolic music generation and revision. Libretto uses an LLM-native grammar with explicit onset slots, voices, and bar-level organization, then evaluates each piece in a corpus-calibrated statistical space over rhythm, harmony, melody, texture, form, and variation. The same structural axes support retrieval, diagnosis, copy-risk control, and iterative self-revision. Across gap filling, reference-guided full-piece generation, gradual morphing, and educational music generation, Libretto turns symbolic music from a raw token sequence into a measurable and editable object for language-model agents. --- ### Safety-Aware Evaluation of LLM-Generated Driver Intervention Messages through Multi-Task Risk Fusion Authors: Keito Inoshita Published: 2026-06-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.22706v1 Existing driver intervention systems rely on auditory alerts and fixed templates, failing to leverage multi-task recognition outputs. General-purpose metrics such as BLEU and BERTScore cannot capture intervention-specific quality dimensions including risk-urgency alignment, cognitive load, and driver acceptability. In this paper, we propose the Driver Safety-Aware Intervention Score (DSAIS), a domain-specific metric evaluating five dimensions through a hybrid architecture combining lightweight rule-based computation with LLM Judge evaluation, together with an end-to-end framework integrating four-task recognition outputs into an LLM through risk fusion, state history management, and dynamic prompt construction. Experiments on the AIDE dataset with five models and seven conditions demonstrate that DSAIS achieves ICC 0.798-0.840 across three architecturally distinct judges and Cohen's d > 1.5 across all control conditions. Multi-dimensional sub-score analysis quantifies the contextual adaptability gap between rule-based and LLM-based systems, revealing that multi-task integration improves contextual relevance by 9.1% over rule-based baselines. Ablation experiments demonstrate that each framework component contributes to contextual relevance, with sub-score decomposition revealing gains that aggregate scoring masks. Driver emotion recognition is identified as the most critical upstream factor, and compact local LLMs (7B--9B parameters) achieve quality superior to API-based models, providing practical design guidelines for in-vehicle deployment. --- ### Modular Diffusion Models for Structured Visual Recognition Authors: Siddhesh Khandelwal, Björn Ommer, Leonid Sigal Published: 2026-06-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.22702v1 Traditional supervised methods for structured visual recognition tasks -- such as object detection, segmentation, and scene graph generation -- often produce deterministic, fixed outputs, limiting their ability to capture the inherent uncertainty in complex visual scenes. As a consequence, such point estimates are unable to capture the prediction uncertainty (or multi modality) intrinsic to these problems, often arising from natural ambiguities (e.g., ambiguity in size of partially occluded objects, local ambiguity of exact segmentation boundary, etc.) as well as noise and sparsity of training data. To address this limitation, we present Modular Diffusion Models (MDMs), a simple and novel framework that learns a distribution over structured outputs for a given input image. MDMs decompose the diffusion process into distinct, task-specific modules, each focused on capturing a different aspect of the structured information space, such as object categories, spatial locations, and inter-object relationships. This modular design allows each component to be learned independently, with seamless integration at inference without additional training. Furthermore, the modularity of MDMs enables the diffusion process to easily operate over the heterogeneous output space common in many structured learning tasks (e.g., a continuous bounding boxes and discrete class labels). Experimental results over three distinct structured tasks -- object detection, instance segmentation, and scene graph generation -- highlight the benefits of our proposed framework. --- ### SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors Authors: Osama Wehbi, Sarhad Arisdakessian, Omar Abdel Wahab, Azzam Mourad, Hadi Otrok Published: 2026-06-21 Categories: cs.LG, cs.AI, cs.CR, cs.CV arXiv: https://arxiv.org/abs/2606.22700v1 Federated Learning (FL) enables collaborative model training without sharing raw data, making it a promising paradigm for privacy-sensitive applications. However, its decentralized nature makes it inherently vulnerable to backdoor attacks, where malicious clients embed hidden triggers into local training data to manipulate model predictions. Existing defenses mainly operate during before and during aggregation cannot fully eliminate backdoor behaviors that persist in the converged global model. Moreover, the effectiveness of post-training sanitization is often limited by the server's lack of knowledge of trigger patterns or poisoned clients after convergence, resulting in residual backdoor behaviors or accuracy degradation due to neuron entanglement. To address this limitation, we propose SCRUB-FL (Sanitizing and Cleansing Representations via Unlearning of Backdoors), a two-phase solution for post-training backdoor removal in FL. During training, clients identify suspicious samples using spectral analysis and activation clustering, then train lightweight Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) models to capture trigger-related distributions. The generator parameters are aggregated server-side to construct a global representation of suspicious patterns without exposing raw data. After convergence, the server synthesizes trigger-approximating samples and applies machine unlearning to erase the trigger-target association by redistributing predictions toward a uniform distribution. Experimental evaluations on CIFAR-10 and GTSRB across three attack types and up to 40% malicious participation demonstrate that SCRUB-FL reduces the backdoor attack success rate to as low as 3.88% while maintaining over 91% normal task accuracy, outperforming state-of-the-art defenses without requiring prior trigger knowledge or a large clean proxy dataset at the server. --- ### Catching Lies Without Sending the Video: Privacy-Preserving Multimodal Deception Detection Authors: Nikita Sharma, Pranav Sara, Karan Singla Published: 2026-06-21 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2606.22699v1 Frontier multimodal models can guess whether a person is lying from a testimony video. To do so, they stream that raw face and voice to a third-party model. We ask whether the heavy media is needed at all. On the Real-life Trial Deception dataset, Whissle on-device speech and vision stack extracts a compact digest: transcript, emotion, age, gender, intent distributions, a deception intent filter, fluency and rhythm, per-frame facial behaviour, and prosody. Under speaker-independent evaluation, we report three findings. A small classifier on this digest reaches AUC 0.741, matching Gemini 2.5 Pro on full video. Handing the digest to a frontier LLM reaches AUC 0.755 with Claude Opus 4.8 at 7.8X fewer input tokens, with no media leaving the device. The reported 75% accuracy is a speaker-leakage artifact. We release code and experiments. ---