Aligning AI systems with diverse human values requires value specifications grounded in concrete examples, but generating such examples without extensive human supervision remains an open challenge. We investigate what makes these examples effective, using Internal Coherence Maximization (ICM) -- which infers labels by maximizing their mutual predictability -- to generate persona-specific examples that steer a model toward a target group's values, without human supervision. Across four benchmarks spanning classification, preference, and open-ended generation, ICM-inferred in-context examples match the performance of gold labels. Crucially, coherence matters beyond individual label accuracy: with accuracy held constant, more coherent examples generalize substantially better than incoherent ones. For personas underrepresented in pretraining data, targeted human feedback on the questions where the model is least certain about a persona's values yields better generalization than the same number of labels on arbitrary questions. These results identify coherence as a key design principle for scalable value specification, leveraging the diverse human perspectives already encoded in pretrained language models.

Background: Oral diseases affect nearly 3.5 billion people worldwide, yet the comparative clinical potential of large-scale AI models in dentistry remains poorly understood. Three distinct model categories have emerged: language-generative models, discriminative vision foundation models, and dental-specific foundation models, with no unified review examining their relationships and collective limitations. Methods: Following PRISMA-ScR guidelines, we systematically searched four databases (PubMed, Google Scholar, Scopus, arXiv), screened independently by two reviewers. After applying inclusion/exclusion criteria, 97 studies (2020-2026) were included. We propose a two-dimensional classification framework organizing models by architectural paradigm and dental specialization degree. Results: Language-generative models excel at text-based tasks (clinical reasoning, licensing exams, patient communication) but show inconsistent performance on image-dependent diagnostics. Adapted SAM and CLIP variants achieve strong tooth segmentation and lesion detection results. Dental-specific models (DentVFM, DentVLM, OralGPT) demonstrate strongest performance on complex multimodal tasks. Integrated pipelines consistently outperform single-model approaches. A data asymmetry is observed: dental-specific pretraining concentrates almost entirely in the vision domain, reflecting scarce large-scale dental text corpora. Conclusions: General-purpose and dental-specific models play complementary roles; the most effective systems combine both within structured pipelines. Safe autonomous deployment requires resolving three persistent barriers: hallucination in generative models, limited annotated dental datasets, and absent standardized clinical evaluation benchmarks.

Edge AI nodes for search and rescue are increasingly expected to run computer vision locally, yet ultra-low-end hardware imposes hard constraints on memory, compute, and inter-device communication. This work addresses occlusion-robust object detection on devices with less than 1 MB SRAM by combining an MCUNet backbone, a YOLOv2 detection head, and Lite quantisation. Two collaborative inference strategies are evaluated: feature-level fusion, concatenating intermediate feature maps, and decision-level fusion via Weighted Boxes Fusion (WBF). WBF outperforms feature-level fusion under all tested occlusion conditions, yielding gains of up to +0.2736 mAP in asymmetric scenarios. Extending fusion to three views improves accuracy further (up to +0.3827 mAP) at modest communication overhead (~1.3 KB per exchange). Hardware experiments progress from a host-assisted USB-relay baseline to a Wi-Fi peer-to-peer deployment on two Coral Dev Board Micro units, where WBF executes on-device with negligible communication energy relative to inference. In a 301.9 s autonomous session of 108 frames, fused output is produced on 61 frames versus 47 for a single board - a coverage gain of +29.8%. A decentralised federated learning feasibility note is included but not treated as a primary result, as performance remains limited under non-iid data. The results support decision-level fusion as a viable option for improving occlusion robustness in small-scale edge object detection, including host-free multi-board operation on ultra-low-end hardware.

Deep learning weather models now match numerical weather prediction accuracy while running orders of magnitude faster, but produce deterministic forecasts without uncertainty estimates, a critical gap for high-stakes decisions during extreme weather events. This paper proposes Neural Tangent Kernel-based uncertainty quantification (NTK-UQ) using last-layer empirical features. Theoretical analysis predicts that UQ quality is architecture-dependent through two mechanisms. First, a variance collapse mechanism explains when UQ fails: when the eigenvalue truncation rank approaches the effective rank of the feature space, the GP correction term consumes nearly all prior variance, destroying discrimination between tropical cyclones and routine conditions; architectures with concentrated spectra (spectral operators) require aggressive truncation ($k \leq 10$), while attention-based models tolerate full-rank computation. Second, decomposition performance depends on the non-Gaussian, heavy-tailed structure of extreme weather: Independent Component Analysis exploits higher-order statistics (kurtosis, negentropy) to isolate heavy-tailed extreme-event features, achieving higher discrimination than singular value decomposition, which captures only second-order variance. A data-driven selection rule chooses ICA or SVD from the feature eigenspectrum concentration ratio, correctly prescribing the superior decomposition for all four evaluated architectures. Compared to split conformal prediction (the natural post-hoc baseline), NTK-UQ achieves 31--37\% sharper prediction intervals at 90\% coverage, and uniquely produces \emph{adaptive} intervals that scale with extreme event severity, which conformal prediction cannot achieve by construction. The framework requires no retraining; inference-time uncertainty requires only a single matrix-vector product per sample.

While sim2real efforts are necessary for effective policy transfer to hardware, there is such a thing as too much of a good thing. We argue that sim2real efforts have led to misaligned incentives with policy learning, resulting in simulator lock in and poor policy exploration due to the unreasonable constraints imposed by the real world. We offer a diagnosis and explanation of the current status of the problem, and propose a potential solution via a sim2sim2real paradigm that leverages the robot's kinematics as the sole design constraint.

Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, but real-world deployment requires them to continually acquire new vision-language capabilities, making Multimodal Continual Instruction Tuning (MCIT) essential. To reduce inter-task interference and promote collaboration, recent methods often employ sparse architectures like Mixture of LoRA Experts with image-text similarity routing. However, tasks with distinct response structures could share highly similar visual-linguistic semantics and thus be wrongly routed to the same expert; image-text similarity alone is insufficient for reliable task assignment. For example, an expert in a grounding task requiring coordinate prediction may be biased toward producing short textual answers after learning semantically similar VQA tasks. This format-blind task assignment integrates heterogeneous response types into shared parameters, inducing gradient interference and ineffective expert collaboration. To address this problem, we propose ProtoAda, a prototype-guided adaptive tuning framework. ProtoAda introduces format-aware task prototypes to align task assignment and routing with both task semantics and output structure, and further consolidates format-compatible updates in a geometry-aware manner to effectively reuse and progressively refine existing parameters. Extensive experiments on multiple benchmarks demonstrate that ProtoAda achieves superior performance, especially on tasks whose answer structures are easily corrupted by sequential tuning.

One-step text-to-image generators are attractive for deployment because they generate an image with a single forward pass, but preference finetuning them remains difficult: standard alignment methods often rely on policy likelihoods, denoising trajectories, differentiable reward gradients, or test-time optimization. We propose Drifting Preference Optimization (DrPO), an online preference-finetuning method for deterministic one-step generators. For each prompt, DrPO samples candidates from the current generator, ranks them with a target reward, and uses high- and low-scoring samples to synthesize a feature-space update direction. The update is a non-parametric dipole preference field plus a reference drift estimated from the frozen base generator, and is optimized through a detached feature-space regression target. The target reward is used only for ranking, so DrPO can train with large, black-box, or non-differentiable rewards while inference remains a single generator call. We evaluate DrPO on SD-Turbo and SDXL-Turbo with multiple target rewards and benchmarks, including HPSv3 and GenEval. DrPO improves alignment over reward-gradient-free one-step preference baselines and reduces HPSv3 training computation by $3.51\times$ under the matched effective-batch setting by removing reward-model backpropagation. Initial offline experiments suggest that sample-based gradient synthesis can also be used beyond online reward ranking.

Systematic reviews rely on forest plots to synthesise quantitative evidence across biomedical studies, but generating them remains a fragmented and labour-intensive process. Researchers must interpret complex clinical texts, manually extract outcome data from trials, define appropriate interventions and comparators, harmonise inconsistent study designs, and carry out meta-analytic computations-typically using specialised software that demands structured inputs and domain expertise. While recent work has demonstrated that large language models can extract study-level data from unstructured text, no existing system automates the complete pipeline from raw documents to synthesised forest plots. To address this gap, we introduce AutoForest, the first end-to-end system that generates publication-ready forest plots directly from biomedical papers. Given one or more study papers, AutoForest automatically suggests ICO (Intervention, Comparator, Outcome) elements, extracts outcome data, performs statistical synthesis, and renders the final forest plot. We describe the system architecture, user interface and demonstrate its effectiveness on real-world examples through a user study involving clinicians, showing how AutoForest can accelerate evidence synthesis and substantially lower the barrier to conducting meta-analyses.

Epilepsy is one of the most common neurological disorders globally, characterized by recurring seizures and significantly impacting the quality of life. Despite advancements in diagnostic techniques, the mitigation of risks faced by epilepsy patients remains challenging due to the unpredictability of seizure events. An accurate forecast of seizure onset helps to reduce risks in epilepsy patients. In this paper, we propose EEG-FuseFormer, a transformer-based feature fusion framework for seizure-onset prediction that combines intermediate features extracted from Convolutional Neural Networks-Long Short-Term Memory (CNN-LSTM) and ResNet-18 networks. The CNN-LSTM architecture captures both spatial and temporal features directly from the raw signal, whereas the ResNet-18 extracts features from the Short-Time Fourier Transform (STFT) representation of the EEG signals. Fusion is carried out using a transformer encoder, and the final prediction is generated using fully connected dense layers. The CHB-MIT dataset was used to validate the proposed model. The results show that the proposed model achieves a mean recall of 98.85% and outperforms most of the state-of-the-art methods. This study evaluates the ability of the proposed feature fusion model to generalize in cross-patient testing scenarios. Fine-tuning pre-trained models on limited target patient data (target adaptation) within the cross-patient validation framework results in higher recall, precision, and F1-score metrics in comparison to the conventional cross-patient validation approach. Finally, the runtime-based computational complexity of the model is assessed across diverse hardware platforms to highlight the performance-complexity trade-off.

Autonomous agents are increasingly expected to support end-to-end medical-AI research workflows, moving beyond isolated prediction tasks or short-form clinical question answering. However, existing medical agent benchmarks primarily evaluate final outputs, providing limited visibility into agent behavior within the research process. To address this gap, we present AutoMedBench, a workflow-aware benchmark for autonomous medical-AI research across diverse medical imaging and multimodal inference tasks, organizing agent execution into a unified five-stage workflow (S1-S5): Plan, Setup, Validate, Inference, and Submit. It comprises long-horizon tasks with each run averaging 33 agent turns, spanning five research tracks: segmentation, image enhancement, visual question answering (VQA), report generation, and lesion detection. Each task is evaluated under two difficulty tiers, Lite and Standard, which use the same data and metrics but differ in the amount of task-brief scaffolding, and each run is scored using both final task performance and S1-S5 stage scores, enabling stage-level analysis from the initial task brief to the final submitted artifact. Across thousands of recorded runs, stage-level scoring reveals that Validate is the weakest workflow stage on average, whereas Setup is the strongest, suggesting that current agents are better at making pipelines executable than at verifying their reliability. Post-run error analysis further shows that verification and submission failures dominate tagged errors, accounting for 37.7% and 38.1% of fired codes respectively, whereas task-understanding errors are rare at 0.9%, and runs with one fired error code have a 48% lower overall score than runs with no error code on average.

Auto-harness systems such as A-Evolve, GEPA, and Meta-Harness improve LLM agents by optimizing prompts, skills, tools, memories, and supporting infrastructure from execution feedback, but they are typically evaluated on fixed offline benchmarks. Real deployments instead present open-ended task streams: histories grow without a fixed endpoint, heterogeneous tasks require different harnesses, and problem distributions shift over time. These challenges make a single repeatedly and densely updated harness brittle, causing performance degradation as accuracy peaks early and then declines. This motivates sustained harness construction with task-wise adaptation. We introduce Adaptive Auto-Harness, a framework and system for such streams. The framework decomposes the gap to an oracle harness into evolution loss and adaptation loss. The system addresses these losses with a stateful multi-agent evolver, a harness tree with solve-time routing, and human-steering hooks for cases where history lacks the needed signal. Across prediction-market, security-competition, and event-forecasting streams, Adaptive Auto-Harness outperforms five existing auto-harness baselines and ablations attribute gains to better construction, routing, or targeted human steering. Code is available in \href{https://github.com/A-EVO-Lab/a-evolve/tree/release/adaptive-auto-harness}{Link}.

Generating physically consistent 3D tabletop scenes is a fundamental yet underexplored problem for interactive and generalist robotic learning. The challenge stems from dense object hierarchies and irregular affordances. Here, an interactive scene denotes a physically valid, collision-free environment directly loadable into physics simulators. Existing methods, ranging from decoupled symbolic solvers to end-to-end regression models, often suffer from error propagation or overfitting to noisy supervision containing widespread physical violations. To address these limitations, we introduce PhyScene3D, a framework that reformulates generation as a Human-Mimetic Constructive Process. The proposed Cognitive Topological Reasoning Chain (CTRC) factorizes scene synthesis into a sequential, anchor-conditioned process. It employs a 3D AABB-based placement scheme that imposes a strong structural inductive bias. To address imperfect supervision and physical infeasibility, we introduce Physics-Aware Denoising Alignment (PADA). It integrates a differentiable Signed Distance Field (SDF) with Test-Time Optimization (TTO) to project generated scenes onto a physics-feasible manifold while preserving semantic intent. Experiments demonstrate that PhyScene3D outperforms state-of-the-art approaches in both semantic accuracy and physical validity, achieving a 40% reduction in scene-wise collision rate relative to the human-annotated training data.

Gaussian splatting has shown strong potential for 3D reconstruction and novel view synthesis. However, most existing methods require accurate camera parameters and per-scene optimization, while feed-forward methods with pixel-aligned Gaussian primitives often suffer from artifacts and non-uniform primitives. In this paper, we propose $\text{VG}^2$GT, a Voxel-Gaussian Splatting Visual Geometry-Grounded Transformer. $\text{VG}^2$GT leverages a frozen pretrained visual foundation model (VFM), incorporates a multi-scale differentiable voxel module to enhance geometric understanding, and directly splits and regresses Gaussian primitive parameters from voxel features. During training, depth maps are supervised through stochastic solid volume rendering, enabling geometrically accurate Gaussian scene reconstruction while keeping the visual foundation model fully frozen. This design enables $\text{VG}^2$GT to be seamlessly plugged into any patch-feature-based VFM, while substantially reducing the required training cost. $\text{VG}^2$GT outperforms current state-of-the-art methods on widely used DTU, Replica, TAT, and ScanNet datasets.

Clinical diagnosis often requires combining imaging with physiological measurements, yet deployed models typically operate on unimodal data. We present PaCX-MAE, a cross-modal distillation framework that injects physiological priors into chest X-ray (CXR) encoders while remaining strictly unimodal at inference. PaCX-MAE augments in-domain masked autoencoding with a dual contrastive-predictive objective, aligning CXR representations with paired ECG and laboratory embeddings. Extensive evaluation across nine benchmarks demonstrates consistent improvements over domain-specific MAE, particularly on physiology-dependent tasks (e.g., +2.7 AUROC on MedMod; +6.5 F1 on VinDr). The method proves highly label-efficient in the 1% regime and preserves anatomical fidelity, achieving parity with MAE on segmentation tasks. Zero-shot and attention analyses confirm that PaCX-MAE successfully learns to attend to physiological indicators, such as the cardiac silhouette, absent in standard visual pretraining.

We present CART (Context-Anchored Recurrent Transformer), a parameter-efficient language model that reuses a single shared core block R times across depth. Unlike prior looped transformers that recompute key-value tensors at every iteration, CART computes K and V once from a multi-layer prelude and has the recurrent core cross-attend to those frozen tensors via multi-head latent attention. A learned Linear Time-Invariant (LTI) gate keeps the recurrence stable: its spectral radius settles in a narrow band (rho in [0.79, 0.83]) across all 36 fully-trained configurations. We evaluate CART on single consumer GPUs in two stages: a 64-configuration screen at 3,000 steps, then 36 configurations (P=6, R in {6,8,10}, three seeds) trained for 30,500 steps (~1B tokens). Two patterns hold across widths d in {256,512,768,1024}: prelude depth P dominates loop count R, and the Stage-1 ranking of R reverses at full training (R=6 becomes best at d>=512). At the binding d=1024 parameter-parity test, CART does not beat a parameter-matched dense baseline, losing by 1-2% at stored-parameter parity and by ~10% at effective-parameter parity. Diagnostic ablations split the effective-parameter gap into ~5% from weight sharing and a residual ~5% from the heterogeneous prelude/anchor/core/coda framing; the recurrent-core machinery (hyper-connections, LTI gate, loop-index embedding) is individually vestigial. Variable-R inference degrades on both sides of the trained R, a negative result for test-time depth scaling under this recipe.

Retrieval-Augmented Generation (RAG) systems are widely deployed and increasingly influential, but their reliance on external corpora exposes new security risks from poisoned retrieval content. Existing RAG attacks are largely focusing on individual queries or narrow topic-local query sets, which limits their practical reach and offers limited camouflage in real-world settings. In this paper, we introduce discourse-level opinion manipulation, a new threat model in which coordinated influence across a semantic query network induces opinion shifts over a holistic, multi-topic query space. We formalize this threat in a black-box setting and propose DiscourseFlip, an agentic, graph-guided attack that dynamically allocates a limited poisoning budget to maximize discourse-level opinion deviation. Extensive experiments demonstrate that DiscourseFlip consistently induces targeted opinion shifts across the contextualized query network and significantly outperforms existing baselines in terms of coverage and effectiveness. User studies further confirm that DiscourseFlip is effective while remaining well camouflaged from user detection. Moreover, systematic analyses show that existing mitigation strategies are ineffective against discourse-level manipulation, underscoring the urgent need for more robust and adaptive defenses to address discourse-level vulnerabilities.

Visual inspection remains the dominant quality-control practice in woven and tufted carpet production, yet it is slow, subjective, and inconsistent at the line speeds and widths of modern looms. We present a design proposal for an in-line machine-vision system whose primary purpose is twofold: to inspect the carpet web in real time and, equally importantly, to systematically collect and label images of defect patterns so that increasingly capable quality-control models can be trained over the life of the installation. The proposal is grounded in a concrete industrial setting: a Six Sigma (DMAIC) project at a woven-carpet production facility that anticipated a production bottleneck following the installation of additional weaving machines, with a substantial baseline defect rate and significant financial exposure associated with quality failures. We describe an imaging subsystem based on synchronized line-scan cameras with combined bright-field and grazing illumination, derive the resolution and throughput requirements needed to resolve fine structural defects across a multi-metre web, and define a carpet-specific defect taxonomy. We then lay out a staged modelling strategy that begins with unsupervised anomaly detection trained on defect-free material, following the paradigm exemplified by the carpet category of the MVTec Anomaly Detection benchmark, and matures through a human-in-the-loop annotation flywheel into supervised detection and segmentation models. Finally, we connect detection performance to the DMAIC objectives, showing how reductions in escaped defects translate into improved process quality and process sigma levels. The contribution is an end-to-end, deployable blueprint that treats data collection as a first-class engineering objective rather than an afterthought.

For low-altitude Unmanned Aerial Vehicle (UAV) autonomy, 3D spatial understanding is not merely a perception objective, but the safety interface between human instructions and physical flight. In human-scale urban airspace below 20 meters, thin geometry, occlusions, vegetation, and urban clutter define whether an aerial agent can safely enter the space ahead. However, existing UAV datasets mainly provide 2D annotations or 3D boxes, while driving-oriented occupancy benchmarks assume stable ground-level sensor rigs. Both miss the defining regime of low-altitude flight: a front-facing monocular camera observing occupied and free space from a moving aerial body with frame-wise changing 6-DoF pose and camera extrinsics. To bridge this gap, we introduce SkyShield, to the best of our knowledge the first front-view monocular semantic occupancy benchmark for urban UAV flight below 20 meters. Built on CARLA, SkyShield contains 36K front-view UAV samples across diverse urban scenes and weather conditions, pairing each image with frame-wise 6-DoF UAV pose, frame-wise dynamic camera geometry, UAV states, and front-frustum semantic occupancy labels. We further propose KAR-mIoU, a UAV-centric and dynamics-aware metric that re-weights voxel-level evaluation by kinematic reachability and time-to-collision, revealing safety-critical risks hidden by conventional mIoU. To tackle this challenging new setting, we provide SkyOcc, a geometry-first monocular baseline that integrates frame-wise UAV attitude into projection, fuses temporal occupancy features, and applies safety-prior optimization to preserve sparse collision-critical structures. Together, SkyShield, KAR-mIoU, and SkyOcc establish occupancy as a safety interface for low-altitude aerial autonomy. Code and dataset will be released publicly.

Learning long-range non-stationary temporal patterns remains a core challenge for modern sequence models, particularly in strict streaming settings. In these settings, data arrive sequentially and must be processed in a single pass without simultaneously revisiting past observations. Standard architectures, including recurrent neural networks and transformers, are constrained by either truncated backpropagation through time horizon or explicit input window length for long range credit assignment. To address these limitations, we propose SHARP (Sleep-based Hierarchical Accelerated Replay), a framework that decomposes temporal learning into two complementary components: a memory module that accumulates a structured history of past inputs, and a pattern-recognition module that operates over this memory. This separation enables resource- and compute-efficient adaptation to non-stationary dynamics by eliminating the need for backpropagation through time across many steps for long-range credit assignment. Inspired by the accelerated replay observed in rodents during slow-wave sleep, SHARP incorporates offline (sleep) phases in which temporally structured memory traces are replayed in an accelerated form and integrated into higher-level memory representations, improving long-range context retention. Through controlled simulations and ablation studies, we characterize the key properties of the proposed framework. In benchmark datasets such as text8 and PG-19, we demonstrate that SHARP improves over recurrent baselines by retaining next-token predictive performance on previously seen data while continuing to learn from the current stream and generalizing to future unseen data. These gains are enabled by its hierarchical structure, which yields an exponentially increasing effective temporal context with only linear-time computational cost.

Sparse autoencoder (SAE) features are increasingly used to interpret language models, with auto-generated natural-language labels serving as the primary interface for understanding what each feature represents. We ask whether these labels generalize: does a feature labeled for a concept actually track that concept across languages and scripts? Using Serbian digraphia as a controlled testbed--the same language written in both Latin and Cyrillic via deterministic transliteration--we first find that SAE feature sets activated by the same content in different languages, scripts, and wordings share substantial overlap (mean Jaccard 0.39 vs. 0.13 random baseline, peaking at 0.57), suggesting genuine cross-lingual semantic features. We then test whether auto-interpretation labels keep pace. They often do not: features whose labels describe semantic content miss the same meaning in Serbian up to 4x more often thanwithin English, and miss Serbian Cyrillic more than Serbian Latin--two scripts that are deterministic transliterations of each other--suggesting the failures align with how well each form is represented in training. The gap grows with network depth, yet the labels give no indication that they fail. These results suggest that auto-interpretation labels may reflect a feature's behavior on well-represented inputs rather than the concept itself.

Human Activity Recognition (HAR) from ambient sensors enables smart-home applications such as health monitoring and assisted living. In realistic deployments, however, sensor events arrive as a continuous stream and activity boundaries are unknown. Sliding-window inference therefore produces many windows that straddle transitions and contain mixed activities, creating boundary contamination that violates the pre-segmented instance assumption used by most benchmarks and models. Moreover, many pipelines under-use spatial context by treating sensor IDs as independent tokens. We present LastAct, a trajectory-centric framework for streaming smart-home HAR that targets the most recent activity under mixed windows while explicitly modeling spatial structure. LastAct projects sensor events onto the home floorplan to form a layout-aligned trajectory image sequence that preserves spatial continuity. A lightweight gate identifies contaminated windows, and a boundary localizer estimates the last transition to enable boundary-guided masking that emphasizes post-boundary evidence and suppresses stale context. For efficiency, we reuse a precomputed layout-aligned template cache to avoid repeated rendering. Empirically, across four public smart-home datasets under near-realistic mixed-activity protocols, LastAct achieves competitive or superior performance on pure windows and yields substantial Macro-F1 gains on cross/mixed windows, demonstrating improved robustness under near-realistic sliding-window regimes.

Multi-party dialogue discourse parsing aims to identify dependency structures and relation types between utterances in conversations. Previous studies are mostly limited to textual modality or two-party dialogue, failing to meet the multimodal and multi-party settings. In this paper, we construct the first publicly available English multimodal dataset DraDDP for multi-party dialogue discourse parsing, based on American TV dramas. DraDDP contains 495 dialogue segments with 6,374 utterances and 9.1 hours of parallel video content, covering rich multi-party interaction scenarios. Moreover, we establish comprehensive benchmarks by evaluating this task on DraDDP and conducting in-depth analysis on the impact of different modalities. Experimental results demonstrate the value of multimodal information in capturing dialogue structures and relation types. We will publicly release the dataset, annotation guidelines, and code to promote future research in multimodal dialogue understanding.

Despite Bengali being the sixth most spoken language in the world, no prior work has systematically evaluated hallucination in large language models (LLMs) for Bengali. We introduce BenHalluEval, a fine-grained hallucination evaluation framework for Bengali covering four tasks: Generative Question Answering (GQA), Bangla-English Code-Mixed QA, Summarization, and Reasoning. We construct 12,000 hallucinated candidates using GPT-5.4 across twelve task-specific hallucination types, drawn from three existing Bengali datasets, and evaluate seven LLMs spanning reasoning-oriented, multilingual, and Bengali-centric categories under a dual-track protocol that independently measures false-positive rate on ground-truth instances (Track A) and hallucination detection rate on hallucinated candidates (Track B). To jointly penalise both failure modes and prevent inflated scores from uniform response bias, we propose BenHalluScore, a dual-track calibration metric that ranges from 7.72% to 55.42% across models and tasks, revealing substantial variation in hallucination calibration. Chain-of-thought prompting, applied as a mitigation strategy, shifts response distributions without consistently improving hallucination discrimination. BenHalluEval establishes the first dedicated hallucination benchmark for Bengali and highlights the inadequacy of single-track and prompting-only evaluation approaches for low-resource language settings. The dataset and code are available at https://anonymous.4open.science/r/BanglaHalluEval-EB77.

Real-world image restoration (IR) is bottlenecked by the scarcity of high-quality paired training data. Synthetic datasets are abundant but often fail to model real-world degradations, while real-world paired datasets are expensive and difficult to capture. As a result, IR models trained on these datasets show limited generalization in real-world scenarios. In this work, we propose Generative Ground Truth (GGT) by using generative multimodal foundation models (MFMs) to produce high-quality (HQ) targets from real-world low-quality (LQ) images. We first conduct a systematic evaluation of nine state-of-the-art MFMs, including Nano-Banana-2 and GPT-Image-2, on images of various scenes and degradation types. The results demonstrate that Nano-Banana-2 with VLM-based adaptive prompting shows the highest capability to synthesize perceptually realistic and content-faithful HQ targets, which can serve as the GGT for the LQ input. We then employ Nano-Banana-2 to build a GGT synthesis pipeline, which involves multi-stage quality control to ensure data reliability, and construct GGT-100K, an LQ-HQ paired dataset comprising 103,707 training pairs and covering diverse scenes and complex real-world degradations. A test set of 500 image pairs is also established. Extensive experiments show that GGT-100K consistently improves the real-world generalization of a wide range of IR models, with particularly strong benefits for finetuning generative models for IR tasks. Our results suggest that MFMs can serve as practical tools for restoration-oriented data generation, and GGT-100K is a useful resource to expand the generalization boundaries of real-world IR models.

LLM-based research agents have advanced rapidly in science and engineering, where research is organized around executable experiments, code, and quantitative signals. Humanities scholarship, however, requires a different mode of reasoning: interpretive, evidence-grounded argument over primary sources, where scholarly value depends on faithful quotation, verifiable provenance, and close reading. Existing research agents remain largely optimized for execution and retrieval, not evidence-grounded interpretive reasoning. To address this gap, we introduce SPIRE (Scholarly-Primitives-Inspired Research Engine), a multi-agent framework for evidence-grounded humanities scholarship. Drawing on Scholarly Primitives theory, SPIRE casts recurring humanities operations as cooperating agent roles (source discovery, evidence annotation, comparison, provenance checking, sampling, citation binding, and argumentative synthesis) over a multi-scale close-reading substrate of passages, intra-context graph communities, and cross-context semantic clusters. On a peer-reviewed-paper benchmark over classical Chinese and Greco-Roman Latin scholarship, SPIRE recovers cited primary-source evidence more reliably than Naive LLM, Text RAG, and GraphRAG, and receives higher blind-judge scores on answer accuracy, depth, coverage, and evidence quality. Ablations show that both the scholarly-operation agents and close-reading retrieval contribute to evidence-grounded essays. Code, data catalogues, and reproduction scripts are released at https://github.com/YatingPan/SPIRE.

Geometry-aware generative models and novel view synthesis approaches have shown strong potential in visual fidelity and consistency. In parallel, equivariant representation learning has emerged as a powerful framework for constructing latent spaces where analytically known group transformations could act directly, capturing geometric structure in data and enhancing both interpretability and generalization in novel view synthesis. However, we identify that existing approaches often suffer from latent misalignment, a discrepancy between the intended group action and the actually required transformations in the latent space. Consequently, the learned latents often fail to consistently preserve the equivariant relations imposed by the underlying group symmetry. To address this, we propose Residual Latent Flow, a flow-based framework that corrects the misaligned latents, thereby improving compliance with the underlying equivariance relation. Our comprehensive experiments show that our method significantly reduces latent misalignment and improves novel view synthesis quality, under rotation groups SO(n).

Drawing on Ullmann-Margalit's concept of opting (transformative, irrevocable, and shadowed by foreclosed alternatives), we show that current AI systems raise a profound ethical problem that existing AI ethics has not fully captured: the illusion of opting, in which persons and groups encounter the deceptive appearance of meaningful consequential choice while the agency needed to become genuinely capable of choosing is weakened. Against approaches that treat AI primarily as an optimizer of already given ends, we argue that AI systems should be evaluated by whether they protect and cultivate meta-capacity against the illusion of opting: the socially and institutionally scaffolded agentive capacity through which means and ends can be formed, contested, revised, and owned. This reframing is especially urgent for disadvantaged populations, who are least able to absorb the costs of the illusion of opting when AI-mediated pathways misdirect behavior and action. We propose three normative imperatives for AI-mediated consequential decisions: existential honesty, which acknowledges the limits of prediction; ecological rationality, which situates guidance within heterogeneous lived ecologies; and counterfactual reparation, which acknowledges and repairs foreclosed alternatives when AI-mediated decision-making pathways fail.

Estimating individual treatment effect (ITE) from observational graph data is crucial for decision-making in the fields such as commerce and medicine. This task is challenging due to interference, where individual outcomes can be influenced by the treatments and covariates of their neighbors. Existing methods attempt to model such interference for accurate ITE estimation. However, a critical issue is often overlooked: differentiated networked effect (DNE), an effect caused by local networks consisting of neighbors with varying importance and scales. Capturing DNE is vital; otherwise, we will end up with imprecise ITE estimation due to an erroneous characterization of interference, which can result in misguided decisions. To address this challenge, we propose a novel interference modeling mechanism that incorporates two partial attention mechanisms and a message amplifier. The partial attention mechanisms automatically estimate the importance of different neighbors in contributing to interference, while the message amplifier adjusts the results of the interference modeling mechanism based on the scale of neighbors, all of which enables the model to capture DNE. Experiments on three real-world graphs demonstrate that our methods outperform existing approaches for ITE estimation from graph data, which corroborates the importance of explicitly capturing DNE.

Many open-ended instructions have multiple valid answers that users can benefit from seeing, but post-training often narrows an LLM's output space toward a small set of canonical responses. We introduce REDIPO, an offline DPO data-construction pipeline for recovering distinct valid answer modes while preserving the alignment benefits of the instruct model. For each prompt, REDIPO samples responses from both base and instruct models, rewrites base-model responses with the instruct model, filters candidates for safety and instruction-following quality, and builds preference pairs that favor marginally diverse responses among candidates with similar instruction-following reward. Across Qwen3-4B, OLMo-3-7B, and LLaMA-3.1-8B, REDIPO improves NoveltyBench distinct_k by 134%, 33%, and 44% relative to the instruct checkpoints, while DivPO changes diversity by 0%, -6%, and -4% on the same models. These gains largely maintain MTBench, IFEval, and Arena-Hard performance, and reduce direct-category HarmBench attack success rate. Ablations show that marginal-diversity pair selection and base-response rewriting drive the diversity gains, while filtering and quality-bounded pairing help maintain alignment. Overall, our results show that diverse valid answers from base-model generations can be reintroduced through carefully constructed preference data while retaining the alignment benefits of post-training. We release our code and data at https://github.com/vsamuel2003/ReDiPO.

Large Language Models (LLMs) have advanced autonomous agents from deep search, which retrieves concise factual answers, to deep research, which synthesizes scattered evidence into long-form reports. However, verifiable multimodal deep research remains challenging due to open-ended synthesis without deterministic ground truth and the need to interleave textual arguments with visual evidence. We propose Ptah, a multi-agent harness for interleaved report generation. Ptah orchestrates the lifecycle from user query to rendered web report through planning, research, and writing stages, where specialized agents construct visual-aware plans, collect claim-grounded evidence, maintain source-aligned images in a Visual Working Memory, and compose reports through declarative multimodal tool use. A verifier agent serves as the harness's acceptance function, enforcing factual grounding, citation fidelity, and cross-modal consistency throughout the workflow. We further introduce PtahEval, an evaluation protocol that augments existing benchmarks with image-level and presentation-level assessments. Experiments on deep research benchmarks show that Ptah produces more reliable, visually informative, and usable human-facing multimodal reports than strong baselines. Our code is released at https://github.com/SnowNation101/Ptah