Medicine is an empirical discipline refined through long-term observation and the messy, high-variance reality of clinical practice. Physicians build diagnostic and therapeutic competence through repeated cycles of application, reflection, and improvement, forming individualized methodologies. Yet outcomes vary widely, and master physicians' knowledge systems are slow to develop and hard to transmit at scale, contributing to the scarcity of high-quality clinical expertise. To address this, we propose Med-Shicheng, a general framework that enables large language models to systematically learn and transfer distinguished physicians' diagnostic-and-therapeutic philosophy and case-dependent adaptation rules in a standardized way. Built on Tianyi, Med-Shicheng consists of five stages. We target five National Masters of Chinese Medicine or distinguished TCM physicians, curate multi-source materials, and train a single model to internalize all five knowledge systems across seven tasks, including etiology-pathogenesis analysis, syndrome diagnosis, treatment principle selection, prescription generation, prescription explanation, symptom evolution with regimen adjustment, and clinical advice. Implemented on Qwen2.5-1.5B-Base, Med-Shicheng runs on resource-constrained GPUs while achieving performance comparable to DeepSeek-R1 and GPT-5. We also examine the reliability of LLM-as-a-judge versus physician evaluation: automated judging tracks overall trends but shows bias on fine-grained individualized distinctions, highlighting the need for physician involvement when ground truth is unavailable and for domain-adapted judge models.

Large Language Models (LLMs) have demonstrated impressive capabilities across various specialist domains and have been integrated into high-stakes areas such as medicine. However, as existing medical-related benchmarks rarely stress-test the long-context memory, interference robustness, and safety defense required in practice. To bridge this gap, we introduce MedMT-Bench, a challenging medical multi-turn instruction following benchmark that simulates the entire diagnosis and treatment process. We construct the benchmark via scene-by-scene data synthesis refined by manual expert editing, yielding 400 test cases that are highly consistent with real-world application scenarios. Each test case has an average of 22 rounds (maximum of 52 rounds), covering 5 types of difficult instruction following issues. For evaluation, we propose an LLM-as-judge protocol with instance-level rubrics and atomic test points, validated against expert annotations with a human-LLM agreement of 91.94\%. We test 17 frontier models, all of which underperform on MedMT-Bench (overall accuracy below 60.00\%), with the best model reaching 59.75\%. MedMT-Bench can be an essential tool for driving future research towards safer and more reliable medical AI. The benchmark is available in https://openreview.net/attachment?id=aKyBCsPOHB&name=supplementary_material

General-purpose embedding models excel at recognizing semantic similarities but fail to capture the characteristics of texts specified by user instructions. In contrast, instruction-tuned embedders can align embeddings with textual instructions yet cannot autonomously infer latent corpus structures, such as determining the optimal number of clusters. To address both limitations, we reframe instruction-following clustering as a generative task and train large reasoning models (LRMs) as autonomous clustering agents. Our reasoning-driven training pipeline enables LRMs to interpret high-level clustering instructions and then infer the corresponding latent groupings. To evaluate this paradigm, we introduce ReasonCluster, a comprehensive benchmark comprising 28 diverse tasks spanning daily dialogue, legal cases, and financial reports. Experiments across diverse datasets and clustering scenarios show that our approach consistently outperforms strong embedding-based methods and LRM baselines, demonstrating that explicit reasoning fosters more faithful and interpretable instruction-based clustering.

Accuracy-based evaluation cannot reliably distinguish genuine generalization from shortcuts like memorization, leakage, or brittle heuristics, especially in small-data regimes. In this position paper, we argue for mechanism-aware evaluation that combines task-relevant symbolic rules with mechanistic interpretability, yielding algorithmic pass/fail scores that show exactly where models generalize versus exploit patterns. We demonstrate this on NL-to-SQL by training two identical architectures under different conditions: one without schema information (forcing memorization), one with schema (enabling grounding). Standard evaluation shows the memorization model achieves 94% field-name accuracy on unseen data, falsely suggesting competence. Our symbolic-mechanistic evaluation reveals this model violates core schema generalization rules, a failure invisible to accuracy metrics.

Improving the accuracy and reliability of medical coding reduces clinician burnout and supports revenue cycle processes, freeing providers to focus more on patient care. However, automating the assignment of ICD-10-CM and CPT codes from clinical documentation remains a challenge due to heterogeneous records, nuanced coding guidelines, and long-tail distributions. Large language models have been proposed to help or automate specific medical coding tasks. However, foundation models are not explicitly trained for medical coding and zero-shot coding has yielded poor results. We investigate whether a modern open-weight foundation model can be adapted for an expert-level medical coding task using privacy-preserving synthetic training data derived from electronic health records. We fine-tune Llama 3-70B on pairs of clinical notes and gold codes generated from EHR-grounded templates and coding policies, then evaluate exact-code prediction for ICD-10-CM and CPT. A zero-shot baseline with the unadapted model achieved an F1 score of 0.18 for exact code match. After fine-tuning on the synthetic corpus, exact-match F1 exceeded 0.70, representing a large absolute gain across both code systems. Notably, performance remained high on complex categories that often require multi-step clinical reasoning and code composition, including Advanced Illness and Frailty classes, and the model retained its performance on medical comprehension tasks. These results indicate that synthetic, policy-aware data can efficiently teach a general-purpose large language model to support precise medical coding without exposing protected health information. The approach offers a practical path for training coding agents safely and iteratively on specific tasks that represent real-world populations.

Large Language Models appear competent when answering general questions but often fail when pushed into domain-specific details. No existing methodology provides an out-of-the-box solution for measuring how deeply LLMs can sustain accurate responses under adaptive follow-up questioning across arbitrary domains. We present DepthCharge, a domain-agnostic framework that measures knowledge depth through three innovations: adaptive probing that generates follow-up questions based on concepts the model actually mentions, on-demand fact verification from authoritative sources, and survival statistics with constant sample sizes at every depth level. The framework can be deployed on any knowledge domain with publicly verifiable facts, without requiring pre-constructed test sets or domain-specific expertise. DepthCharge results are relative to the evaluator model used for answer checking, making the framework a tool for comparative evaluation rather than absolute accuracy certification. Empirical validation across four diverse domains (Medicine, Constitutional Law, Ancient Rome, and Quantum Computing) with five frontier models demonstrates that DepthCharge reveals depth-dependent performance variation hidden by standard benchmarks. Expected Valid Depth (EVD) ranges from 3.45 to 7.55 across model-domain combinations, and model rankings vary substantially by domain, with no single model dominating all areas. Cost-performance analysis further reveals that expensive models do not always achieve deeper knowledge, suggesting that domain-specific evaluation is more informative than aggregate benchmarks for model selection in professional applications.

Commercial AI scribes cost \$99-600 per physician per month, operate as opaque systems, and do not return data to institutional infrastructure, limiting organizational control over data governance, quality improvement, and clinical workflows. We developed Berta, an open-source modular scribe platform for AI-enabled clinical documentation, and deployed a customized implementation within Alberta Health Services (AHS) integrated with their existing Snowflake AI Data Cloud infrastructure. The system combines automatic speech recognition with large language models while retaining all clinical data within the secure AHS environment. During eight months (November 2024 to July 2025), 198 emergency physicians used the system in 105 urban and rural facilities, generating 22148 clinical sessions and more than 2800 hours of audio. The use grew from 680 to 5530 monthly sessions. Operating costs averaged less than \$30 per physician per month, a 70-95% reduction compared to commercial alternatives. AHS has since approved expansion to 850 physicians. This is the first provincial-scale deployment of an AI scribe integrated with existing health system infrastructure. By releasing Berta as open source, we provide a reproducible, cost-effective alternative that health systems can adapt to their own secure environments, supporting data sovereignty and informed evaluation of AI documentation technology.

We present S-Path-RAG, a semantic-aware shortest-path Retrieval-Augmented Generation framework designed to improve multi-hop question answering over large knowledge graphs. S-Path-RAG departs from one-shot, text-heavy retrieval by enumerating bounded-length, semantically weighted candidate paths using a hybrid weighted $k$-shortest, beam, and constrained random-walk strategy, learning a differentiable path scorer together with a contrastive path encoder and lightweight verifier, and injecting a compact soft mixture of selected path latents into a language model via cross-attention. The system runs inside an iterative Neural-Socratic Graph Dialogue loop in which concise diagnostic messages produced by the language model are mapped to targeted graph edits or seed expansions, enabling adaptive retrieval when the model expresses uncertainty. This combination yields a retrieval mechanism that is both token-efficient and topology-aware while preserving interpretable path-level traces for diagnostics and intervention. We validate S-Path-RAG on standard multi-hop KGQA benchmarks and through ablations and diagnostic analyses. The results demonstrate consistent improvements in answer accuracy, evidence coverage, and end-to-end efficiency compared to strong graph- and LLM-based baselines. We further analyze trade-offs between semantic weighting, verifier filtering, and iterative updates, and report practical recommendations for deployment under constrained compute and token budgets.

Document intelligence requires accurate text extraction and reliable reasoning over document content. We introduce \textbf{DISCO}, a \emph{Document Intelligence Suite for COmparative Evaluation}, that evaluates optical character recognition (OCR) pipelines and vision-language models (VLMs) separately on parsing and question answering across diverse document types, including handwritten text, multilingual scripts, medical forms, infographics, and multi-page documents. Our evaluation shows that performance varies substantially across tasks and document characteristics, underscoring the need for complexity-aware approach selection. OCR pipelines are generally more reliable for handwriting and for long or multi-page documents, where explicit text grounding supports text-heavy reasoning, while VLMs perform better on multilingual text and visually rich layouts. Task-aware prompting yields mixed effects, improving performance on some document types while degrading it on others. These findings provide empirical guidance for selecting document processing strategies based on document structure and reasoning demands.

As multimodal language models (MLMs) are increasingly used in social and collaborative settings, it is crucial to evaluate their perspective-taking abilities. Existing benchmarks largely rely on text-based vignettes or static scene understanding, leaving visuospatial perspective-taking (VPT) underexplored. We adapt two evaluation tasks from human studies: the Director Task, assessing VPT in a referential communication paradigm, and the Rotating Figure Task, probing perspective-taking across angular disparities. Across tasks, MLMs show pronounced deficits in Level 2 VPT, which requires inhibiting one's own perspective to adopt another's. These results expose critical limitations in current MLMs' ability to represent and reason about alternative perspectives, with implications for their use in collaborative contexts.

This work identifies a critical failure mode in frontier large language models (LLMs), which we term Internal Safety Collapse (ISC): under certain task conditions, models enter a state in which they continuously generate harmful content while executing otherwise benign tasks. We introduce TVD (Task, Validator, Data), a framework that triggers ISC through domain tasks where generating harmful content is the only valid completion, and construct ISC-Bench containing 53 scenarios across 8 professional disciplines. Evaluated on JailbreakBench, three representative scenarios yield worst-case safety failure rates averaging 95.3% across four frontier LLMs (including GPT-5.2 and Claude Sonnet 4.5), substantially exceeding standard jailbreak attacks. Frontier models are more vulnerable than earlier LLMs: the very capabilities that enable complex task execution become liabilities when tasks intrinsically involve harmful content. This reveals a growing attack surface: almost every professional domain uses tools that process sensitive data, and each new dual-use tool automatically expands this vulnerability--even without any deliberate attack. Despite substantial alignment efforts, frontier LLMs retain inherently unsafe internal capabilities: alignment reshapes observable outputs but does not eliminate the underlying risk profile. These findings underscore the need for caution when deploying LLMs in high-stakes settings. Source code: https://github.com/wuyoscar/ISC-Bench

Retrieval-augmented generation (RAG) is increasingly deployed in enterprise search and document-centric assistants, where responses must be grounded in long and complex source materials. In practice, verifying that generated answers faithfully reflect retrieved documents is difficult: large language models can check long contexts but are too slow and costly for interactive services, while lightweight classifiers operate within strict context limits and frequently miss evidence outside truncated passages. We present the design of a real-time verification component integrated into a production RAG pipeline that enables full-document grounding under latency constraints. The system processes documents up to 32K tokens and employs adaptive inference strategies to balance response time and verification coverage across workloads. We describe the architectural decisions, operational trade-offs, and evaluation methodology used to deploy the verifier, and show that full-context verification substantially improves detection of unsupported responses compared with truncated validation. Our experience highlights when long-context verification is necessary, why chunk-based checking often fails in real documents, and how latency budgets shape model design. These findings provide practical guidance for practitioners building reliable large-scale retrieval-augmented applications. (Model, benchmark, and code: https://huggingface.co/llm-semantic-router)

While Masked Diffusion Language Models (MDLMs) relying on token masking and unmasking have shown promise in language modeling, their computational efficiency and generation flexibility remain constrained by the masking paradigm. In this paper, we propose Deletion-Insertion Diffusion language models (DID) that rigorously formulate token deletion and insertion as discrete diffusion processes, replacing the masking and unmasking processes in current MDLMs. DID improves training and inference efficiency by eliminating two major sources of computational overhead in MDLMs: the computations on non-informative 1) <MASK> tokens inherent to the paradigm, and 2) <PAD> tokens introduced in variable-length settings. Furthermore, DID offers greater flexibility by: 1) natively supporting variable-length sequences without requiring fixed-length padding, and 2) an intrinsic self-correction mechanism during generation due to insertion that dynamically adjusts token positions. To train DID, we design a score-based approach that assigns scores to token insertion operations and derive appropriate training objectives. The objectives involve subsequence counting problems, which we efficiently solve via a parallelized dynamic programming algorithm. Our experiments across fixed and variable-length settings demonstrate the advantage of DID over baselines of MDLMs and existing insertion-based LMs, in terms of modeling performance, sampling quality, and training/inference speed, without any hyperparameter tuning.

The rapid proliferation of large language models (LLMs) in healthcare creates an urgent need for scalable and psychometrically sound evaluation methods. Conventional static benchmarks are costly to administer repeatedly, vulnerable to data contamination, and lack calibrated measurement properties for fine-grained performance tracking. We propose and validate a computerized adaptive testing (CAT) framework grounded in item response theory (IRT) for efficient assessment of standardized medical knowledge in LLMs. The study comprises a two-phase design: a Monte Carlo simulation to identify optimal CAT configurations and an empirical evaluation of 38 LLMs using a human-calibrated medical item bank. Each model completed both the full item bank and an adaptive test that dynamically selected items based on real-time ability estimates and terminated upon reaching a predefined reliability threshold (standard error <= 0.3). Results show that CAT-derived proficiency estimates achieved a near-perfect correlation with full-bank estimates (r = 0.988) while using only 1.3 percent of the items. Evaluation time was reduced from several hours to minutes per model, with substantial reductions in token usage and computational cost, while preserving inter-model performance rankings. This work establishes a psychometric framework for rapid, low-cost benchmarking of foundational medical knowledge in LLMs. The proposed adaptive methodology is intended as a standardized pre-screening and continuous monitoring tool and is not a substitute for real-world clinical validation or safety-oriented prospective studies.

Shape matching is a fundamental task in computer graphics and vision, with deep functional maps becoming a prominent paradigm. However, existing methods primarily focus on learning informative feature representations by constraining pointwise and functional maps, while neglecting the optimization of the spectral basis-a critical component of the functional map pipeline. This oversight often leads to suboptimal matching results. Furthermore, many current approaches rely on conventional, time-consuming functional map solvers, incurring significant computational overhead. To bridge these gaps, we introduce Advanced Functional Maps, a framework that generalizes standard functional maps by replacing fixed basis functions with learnable ones, supported by rigorous theoretical guarantees. Specifically, the spectral basis is optimized through a set of learned inhibition functions. Building on this, we propose the first unsupervised spectral basis learning method for robust non-rigid 3D shape matching, enabling the joint, end-to-end optimization of feature extraction and basis functions. Our approach incorporates a novel heat diffusion module and an unsupervised loss function, alongside a streamlined architecture that bypasses expensive solvers and auxiliary losses. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art feature-learning approaches, particularly in challenging non-isometric and topological noise scenarios, while maintaining high efficiency. Finally, we reveal that optimizing basis functions is equivalent to spectral convolution, where inhibition functions act as filters. This insight enables enhanced representations inspired by spectral graph networks, opening new avenues for future research. Our code is available at https://github.com/LuoFeifan77/Unsupervised-Spectral-Basis-Learning.

Object skeletons offer a concise representation of structural information, capturing essential aspects of posture and orientation that are crucial for autonomous driving applications. However, a unified architecture that simultaneously handles multiple instances and categories using only the input image remains elusive. In this paper, we introduce PoseDriver, a unified framework for bottom-up multi-category skeleton detection tailored to common objects in driving scenarios. We model each category as a distinct task to systematically address the challenges of multi-task learning. Specifically, we propose a novel approach for lane detection based on skeleton representations, achieving state-of-the-art performance on the OpenLane dataset. Moreover, we present a new dataset for bicycle skeleton detection and assess the transferability of our framework to novel categories. Experimental results validate the effectiveness of the proposed approach.

The expansion of generative AI and LLM services underscores the growing need for adaptive mechanisms to select an appropriate available model to respond to a user's prompts. Recent works have proposed offline and online learning formulations to identify the optimal generative AI model for an input prompt, based solely on maximizing prompt-based fidelity evaluation scores, e.g., CLIP-Score in text-to-image generation. However, such fidelity-based selection methods overlook the diversity of generated outputs, and hence, they can fail to address potential diversity shortcomings in the generated responses. In this paper, we introduce the Diversity-Aware Kernelized Upper Confidence Bound (DAK-UCB) method as a contextual bandit algorithm for the online selection of generative models with diversity considerations. The proposed DAK-UCB method incorporates both fidelity and diversity-related metrics into the selection process. We design this framework based on prompt-aware diversity score functions that decompose to a two-sample-based expectation over prompt-output pairs in the previous generation rounds. Specifically, we illustrate the application of our framework using joint kernel distance and kernel entropy measures. Our experimental results demonstrate the effectiveness of DAK-UCB in promoting diversity-aware model selection while maintaining fidelity in the generations for a sequence of prompts. The code is available at https://github.com/Donya-Jafari/DAK-UCB.

Whole Slide Images (WSIs) exhibit hierarchical structure, where diagnostic information emerges from cellular morphology, regional tissue organization, and global context. Existing Computational Pathology (CPath) Multimodal Large Language Models (MLLMs) typically compress an entire WSI into a single embedding, which hinders fine-grained grounding and ignores how pathologists synthesize evidence across different scales. We introduce \textbf{MLLM-HWSI}, a Hierarchical WSI-level MLLM that aligns visual features with pathology language at four distinct scales, cell as word, patch as phrase, region as sentence, and WSI as paragraph to support interpretable evidence-grounded reasoning. MLLM-HWSI decomposes each WSI into multi-scale embeddings with scale-specific projectors and jointly enforces (i) a hierarchical contrastive objective and (ii) a cross-scale consistency loss, preserving semantic coherence from cells to the WSI. We compute diagnostically relevant patches and aggregate segmented cell embeddings into a compact cellular token per-patch using a lightweight \textit{Cell-Cell Attention Fusion (CCAF)} transformer. The projected multi-scale tokens are fused with text tokens and fed to an instruction-tuned LLM for open-ended reasoning, VQA, report, and caption generation tasks. Trained in three stages, MLLM-HWSI achieves new SOTA results on 13 WSI-level benchmarks across six CPath tasks. By aligning language with multi-scale visual evidence, MLLM-HWSI provides accurate, interpretable outputs that mirror diagnostic workflows and advance holistic WSI understanding. Code is available at: \href{https://github.com/BasitAlawode/HWSI-MLLM}{GitHub}.

Training generative models with limited data presents severe challenges of mode collapse. A common approach is to adapt a large pretrained generative model upon a target domain with very few samples (fewer than 10), known as few-shot generative model adaptation. However, existing methods often suffer from forgetting source domain identity knowledge during adaptation, which degrades the quality of generated images in the target domain. To address this, we propose Identity Injection and Preservation (I$^2$P), which leverages identity injection and consistency alignment to preserve the source identity knowledge. Specifically, we first introduce an identity injection module that integrates source domain identity knowledge into the target domain's latent space, ensuring the generated images retain key identity knowledge of the source domain. Second, we design an identity substitution module, which includes a style-content decoupler and a reconstruction modulator, to further enhance source domain identity preservation. We enforce identity consistency constraints by aligning features from identity substitution, thereby preserving identity knowledge. Both quantitative and qualitative experiments show that our method achieves substantial improvements over state-of-the-art methods on multiple public datasets and 5 metrics.

High-quality and controllable digital twins of surgical instruments are critical for Real2Sim in robot-assisted surgery, as they enable realistic simulation, synthetic data generation, and perception learning under novel poses. We present Instrument-Splatting++, a monocular 3D Gaussian Splatting (3DGS) framework that reconstructs surgical instruments as a fully controllable Gaussian asset with high fidelity. Our pipeline starts with part-wise geometry pretraining that injects CAD priors into Gaussian primitives and equips the representation with part-aware semantic rendering. Built on the pretrained model, we propose a semantics-aware pose estimation and tracking (SAPET) method to recover per-frame 6-DoF pose and joint angles from unposed endoscopic videos, where a gripper-tip network trained purely from synthetic semantics provides robust supervision and a loose regularization suppresses singular articulations. Finally, we introduce Robust Texture Learning (RTL), which alternates pose refinement and robust appearance optimization, mitigating pose noise during texture learning. The proposed framework can perform pose estimation and learn realistic texture from unposed videos. We validate our method on sequences extracted from EndoVis17/18, SAR-RARP, and an in-house dataset, showing superior photometric quality and improved geometric accuracy over state-of-the-art baselines. We further demonstrate a downstream keypoint detection task where unseen-pose data augmentation from our controllable instrument Gaussian improves performance.

Sparse Autoencoders uncover thousands of features in vision models, yet explaining these features without requiring human intervention remains an open challenge. While previous work has proposed generating correlation-based explanations based on top activating input examples, we present a fundamentally different alternative based on causal interventions. We leverage the structure of Vision-Language Models and steer individual SAE features in the vision encoder after providing an empty image. Then, we prompt the language model to explain what it ``sees'', effectively eliciting the visual concept represented by each feature. Results show that Steering offers an scalable alternative that complements traditional approaches based on input examples, serving as a new axis for automated interpretability in vision models. Moreover, the quality of explanations improves consistently with the scale of the language model, highlighting our method as a promising direction for future research. Finally, we propose Steering-informed Top-k, a hybrid approach that combines the strengths of causal interventions and input-based approaches to achieve state-of-the-art explanation quality without additional computational cost.

Inference-time scaling has emerged as an effective way to improve generative models at test time by using a verifier to score and select candidate outputs. A common choice is to employ Multimodal Large Language Models (MLLMs) as verifiers, which can improve performance but introduce substantial inference-time cost. Indeed, diffusion pipelines operate in an autoencoder latent space to reduce computation, yet MLLM verifiers still require decoding candidates to pixel space and re-encoding them into the visual embedding space, leading to redundant and costly operations. In this work, we propose Verifier on Hidden States (VHS), a verifier that operates directly on intermediate hidden representations of Diffusion Transformer (DiT) single-step generators. VHS analyzes generator features without decoding to pixel space, thereby reducing the per-candidate verification cost while improving or matching the performance of MLLM-based competitors. We show that, under tiny inference budgets with only a small number of candidates per prompt, VHS enables more efficient inference-time scaling reducing joint generation-and-verification time by 63.3%, compute FLOPs by 51% and VRAM usage by 14.5% with respect to a standard MLLM verifier, achieving a +2.7% improvement on GenEval at the same inference-time budget.

Photovoltaic (PV) power forecasting in edge-enabled grids requires balancing forecasting accuracy, robustness under weather-driven distribution shifts, and strict latency constraints. Existing models work well under normal conditions but often struggle with rare ramp events and unexpected weather changes. Relying solely on cloud-based large models often leads to significant communication delays, which can hinder timely and efficient forecasting in practical grid environments. To address these issues, we propose a condition-adaptive cloud-edge collaborative framework *CAPE* for PV forecasting. *CAPE* consists of three main modules: a site-specific expert model for routine predictions, a lightweight edge-side model for enhanced local inference, and a cloud-based large retrieval model that provides relevant historical cases when needed. These modules are coordinated by a screening module that evaluates uncertainty, out-of-distribution risk, weather mutations, and model disagreement. Furthermore, we employ a Lyapunov-guided routing strategy to dynamically determine when to escalate inference to more powerful models under long-term system constraints. The final forecast is produced through adaptive fusion of the selected model outputs. Experiments on two real-world PV datasets demonstrate that *CAPE* achieves superior performance in terms of forecasting accuracy, robustness, routing quality, and system efficiency.

The Brain Tumor Reporting and Data System (BT-RADS) standardizes post-treatment MRI response assessment in patients with diffuse gliomas but requires complex integration of imaging trends, medication effects, and radiation timing. This study evaluates an end-to-end multi-agent large language model (LLM) and convolutional neural network (CNN) system for automated BT-RADS classification. A multi-agent LLM system combined with automated CNN-based tumor segmentation was retrospectively evaluated on 509 consecutive post-treatment glioma MRI examinations from a single high-volume center. An extractor agent identified clinical variables (steroid status, bevacizumab status, radiation date) from unstructured clinical notes, while a scorer agent applied BT-RADS decision logic integrating extracted variables with volumetric measurements. Expert reference standard classifications were established by an independent board-certified neuroradiologist. Of 509 examinations, 492 met inclusion criteria. The system achieved 374/492 (76.0%; 95% CI, 72.1%-79.6%) accuracy versus 283/492 (57.5%; 95% CI, 53.1%-61.8%) for initial clinical assessments (+18.5 percentage points; P<.001). Context-dependent categories showed high sensitivity (BT-1b 100%, BT-1a 92.7%, BT-3a 87.5%), while threshold-dependent categories showed moderate sensitivity (BT-3c 74.8%, BT-2 69.2%, BT-4 69.3%, BT-3b 57.1%). For BT-4, positive predictive value was 92.9%. The multi-agent LLM system achieved higher BT-RADS classification agreement with expert reference standard compared to initial clinical scoring, with high accuracy for context-dependent scores and high positive predictive value for BT-4 detection.

Facial expression recognition relies on facial data that inherently expose identity and thus raise significant privacy concerns. Current privacy-preserving methods typically fail in realistic open-set video settings where identities are unknown, and identity labels are unavailable. We propose a two-stage framework for video-based privacy-preserving FER in challenging open-set settings that requires no identity labels at any stage. To decouple privacy and utility, we first train an identity-suppression network using intra- and inter-video knowledge priors derived from real-world videos without identity labels. This network anonymizes identity while preserving expressive cues. A subsequent denoising module restores expression-related information and helps recover FER performance. Furthermore, we introduce a falsification-based validation method that uses recognition priors to rigorously evaluate privacy robustness without requiring annotated identity labels. Experiments on three video datasets demonstrate that our method effectively protects privacy while maintaining FER accuracy comparable to identity-supervised baselines.

Feed-forward 3D Gaussian Splatting methods enable single-pass reconstruction and real-time rendering. However, they typically adopt rigid pixel-to-Gaussian or voxel-to-Gaussian pipelines that uniformly allocate Gaussians, leading to redundant Gaussians across views. Moreover, they lack an effective mechanism to control the total number of Gaussians while maintaining reconstruction fidelity. To address these limitations, we present F4Splat, which performs Feed-Forward predictive densification for Feed-Forward 3D Gaussian Splatting, introducing a densification-score-guided allocation strategy that adaptively distributes Gaussians according to spatial complexity and multi-view overlap. Our model predicts per-region densification scores to estimate the required Gaussian density and allows explicit control over the final Gaussian budget without retraining. This spatially adaptive allocation reduces redundancy in simple regions and minimizes duplicate Gaussians across overlapping views, producing compact yet high-quality 3D representations. Extensive experiments demonstrate that our model achieves superior novel-view synthesis performance compared to prior uncalibrated feed-forward methods, while using significantly fewer Gaussians.

Social biases reflected in language are inherently shaped by cultural norms, which vary significantly across regions and lead to diverse manifestations of stereotypes. Existing evaluations of social bias in large language models (LLMs) for non-English contexts, however, often rely on translations of English benchmarks. Such benchmarks fail to reflect local cultural norms, including those found in Japanese. For instance, Western benchmarks may overlook Japan-specific stereotypes related to hierarchical relationships, regional dialects, or traditional gender roles. To address this limitation, we introduce Japanese cUlture adversarial BiAs benchmarK Under handcrafted creation (JUBAKU), a benchmark tailored to Japanese cultural contexts. JUBAKU uses adversarial construction to expose latent biases across ten distinct cultural categories. Unlike existing benchmarks, JUBAKU features dialogue scenarios hand-crafted by native Japanese annotators, specifically designed to trigger and reveal latent social biases in Japanese LLMs. We evaluated nine Japanese LLMs on JUBAKU and three others adapted from English benchmarks. All models clearly exhibited biases on JUBAKU, performing below the random baseline of 50% with an average accuracy of 23% (ranging from 13% to 33%), despite higher accuracy on the other benchmarks. Human annotators achieved 91% accuracy in identifying unbiased responses, confirming JUBAKU's reliability and its adversarial nature to LLMs.

Evaluating text-guided image editing (TIE) methods remains a challenging problem, as reliable assessment should simultaneously consider perceptual quality, alignment with textual instructions, and preservation of original image content. Despite rapid progress in TIE models, existing evaluation benchmarks remain limited in scale and often show weak correlation with human perceptual judgments. In this work, we introduce TIEdit, a benchmark for systematic evaluation of text-guided image editing methods. TIEdit consists of 512 source images paired with editing prompts across eight representative editing tasks, producing 5,120 edited images generated by ten state-of-the-art TIE models. To obtain reliable subjective ratings, 20 experts are recruited to produce 307,200 raw subjective ratings, which accumulates into 15,360 mean opinion scores (MOSs) across three evaluation dimensions: perceptual quality, editing alignment, and content preservation. Beyond the benchmark itself, we further propose EditProbe, an LLM-based evaluator that estimates editing quality via intermediate-layer probing of hidden representations. Instead of relying solely on final model outputs, EditProbe extracts informative representations from intermediate layers of multimodal large language models to better capture semantic and perceptual relationships between source images, editing instructions, and edited results. Experimental results demonstrate that widely used automatic evaluation metrics show limited correlation with human judgments on editing tasks, while EditProbe achieves substantially stronger alignment with human perception. Together, TIEdit and EditProbe provide a foundation for more reliable and perceptually aligned evaluation of text-guided image editing methods.

Time series classification (TSC) performance depends not only on architectural design but also on the diversity of input representations. In this work, we propose a scalable multi-scale convolutional framework that systematically integrates structured multi-representation inputs for univariate time series. We introduce two architectures: MRMS-Net, a hierarchical multi-scale convolutional network optimized for robustness and calibration, and LMRMS-Net, a lightweight variant designed for efficiency-aware deployment. In addition, we adapt LiteMV -- originally developed for multivariate inputs -- to operate on multi-representation univariate signals, enabling cross-representation interaction. We evaluate all models across 142 benchmark datasets under a unified experimental protocol. Critical Difference (CD) analysis confirms statistically significant performance differences among the top models. Results show that LiteMV achieves the highest mean accuracy, MRMS-Net provides superior probabilistic calibration (lowest NLL), and LMRMS-Net offers the best efficiency-accuracy tradeoff. Pareto analysis further demonstrates that multi-representation multi-scale modeling yields a flexible design space that can be tuned for accuracy-oriented, calibration-oriented, or resource-constrained settings. These findings establish scalable multi-representation multi-scale learning as a principled and practical direction for modern TSC. Reference implementation of MRMS-Net and LMRMS-Net is available at: https://github.com/alagoz/mrmsnet-tsc

Prompt engineering is effective but labor-intensive, motivating automated optimization methods. Existing methods typically require labeled datasets, which are often unavailable, and produce verbose, repetitive prompts. We introduce PrefPO, a minimal prompt optimization approach inspired by reinforcement learning from human feedback (RLHF). Its preference-based approach reduces the need for labeled data and hyperparameter tuning-only a starting prompt and natural language criteria are needed. PrefPO uses an LLM discriminator to express pairwise preferences over model outputs and provide feedback to an LLM optimizer, iteratively improving performance. We evaluate PrefPO on 9 BIG-Bench Hard (BBH) tasks and IFEval-Hard, a newly-curated, challenging subset of IFEval. PrefPO matches or exceeds SOTA methods, including GEPA, MIPRO, and TextGrad, on 6/9 tasks and performs comparably to TextGrad on IFEval-Hard (82.4% vs 84.5%). Unlike other methods, PrefPO can optimize in both labeled and unlabeled settings. Without labels, PrefPO closely matches its labeled performance on 6/9 tasks, proving effective without ground truth. PrefPO also improves prompt hygiene: we find existing methods produce prompts 14.7x their original length or with 34% repetitive content; PrefPO reduces these issues by 3-5x. Furthermore, both LLM and human judges rate PrefPO's prompts higher than TextGrad's. Finally, we identify prompt hacking in prompt optimizers, where methods game evaluation criteria, and find PrefPO is susceptible at half the rate of TextGrad (37% vs 86%), generating fewer brittle, misaligned prompts.