Multimodal Retrieval-Augmented Generation (MRAG) enables Multimodal Large Language Models (MLLMs) to generate responses with external multimodal evidence, and numerous video-based MRAG benchmarks have been proposed to evaluate model capabilities across retrieval and generation stages. However, existing benchmarks remain limited in modality coverage and format diversity, often focusing on single- or limited-modality tasks, or coarse-grained scene understanding. To address these gaps, we introduce CFVBench, a large-scale, manually verified benchmark constructed from 599 publicly available videos, yielding 5,360 open-ended QA pairs. CFVBench spans high-density formats and domains such as chart-heavy reports, news broadcasts, and software tutorials, requiring models to retrieve and reason over long temporal video spans while maintaining fine-grained multimodal information. Using CFVBench, we systematically evaluate 7 retrieval methods and 14 widely-used MLLMs, revealing a critical bottleneck: current models (even GPT5 or Gemini) struggle to capture transient yet essential fine-grained multimodal details. To mitigate this, we propose Adaptive Visual Refinement (AVR), a simple yet effective framework that adaptively increases frame sampling density and selectively invokes external tools when necessary. Experiments show that AVR consistently enhances fine-grained multimodal comprehension and improves performance across all evaluated MLLMs

Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples may inadvertently appear in training sets, compromising the validity of reported performance. While detection methods have been developed for the pre-training and Supervised Fine-Tuning stages, a critical research gap exists for the increasingly significant phase of Reinforcement Learning (RL) post-training. As RL post-training becomes pivotal for advancing LLM reasoning, the absence of specialized contamination detection methods in this paradigm presents a critical vulnerability. To address this, we conduct the first systematic study of data detection within RL post-training scenario and propose Self-Critique. Our method is motivated by a key observation: after RL phase, the output entropy distribution of LLMs tends to collapse into highly specific and sparse modes. Self-Critique probes for the underlying policy collapse, i.e., the model's convergence to a narrow reasoning path, which causes this entropy reduction. To facilitate this research, we also introduce RL-MIA, a benchmark constructed to simulate this specific contamination scenario. Extensive experiments show that Self-Critique significantly outperforms baseline methods across multiple models and contamination tasks, achieving an AUC improvement of up to 30%. Whereas existing methods are close to a random guess for RL-phase contamination, our method makes detection possible.

ABSTRACT While specialized learning-based models have historically dominated image privacy prediction, the current literature increasingly favours adopting large Vision-Language Models (VLMs) designed for generic tasks. This trend risks overlooking the performance ceiling set by purpose-built models due to a lack of systematic evaluation. To address this problem, we establish a zero-shot benchmark for image privacy classification, enabling a fair comparison. We evaluate the top-3 open-source VLMs, according to a privacy benchmark, using task-aligned prompts and we contrast their performance, efficiency, and robustness against established vision-only and multi-modal methods. Counter-intuitively, our results show that VLMs, despite their resource-intensive nature in terms of high parameter count and slower inference, currently lag behind specialized, smaller models in privacy prediction accuracy. We also find that VLMs exhibit higher robustness to image perturbations.

Shoulder disorders, such as frozen shoulder (a.k.a., adhesive capsulitis), are common conditions affecting the health of people worldwide, and have a high incidence rate among the elderly and workers engaged in repetitive shoulder tasks. In regions with scarce medical resources, achieving early and accurate diagnosis poses significant challenges, and there is an urgent need for low-cost and easily scalable auxiliary diagnostic solutions. This research introduces videos captured by consumer-grade devices as the basis for diagnosis, reducing the cost for users. We focus on the innovative application of Multimodal Large Language Models (MLLMs) in the preliminary diagnosis of shoulder disorders and propose a Hybrid Motion Video Diagnosis framework (HMVDx). This framework divides the two tasks of action understanding and disease diagnosis, which are respectively completed by two MLLMs. In addition to traditional evaluation indicators, this work proposes a novel metric called Usability Index by the logical process of medical decision-making (action recognition, movement diagnosis, and final diagnosis). This index evaluates the effectiveness of MLLMs in the medical field from the perspective of the entire medical diagnostic pathway, revealing the potential value of low-cost MLLMs in medical applications for medical practitioners. In experimental comparisons, the accuracy of HMVDx in diagnosing shoulder joint injuries has increased by 79.6\% compared with direct video diagnosis, a significant technical contribution to future research on the application of MLLMs for video understanding in the medical field.

Large language models (LLMs) show strong performance across natural language processing (NLP), mathematical reasoning, and programming, and recent large reasoning models (LRMs) further emphasize explicit reasoning. Yet their computational limits, particularly spatial complexity constrained by finite context windows, remain poorly understood. While recent works often focus on problems within the NP complexity class, we push the boundary by introducing a novel benchmark grounded in two PSPACE-complete regular expression (regex) problems: equivalence decision (RegexEQ) and minimization (RegexMin). PSPACE-complete problems serve as a more rigorous standard for assessing computational capacity, as their solutions require massive search space exploration. We perform a double-exponential space exploration to construct a labeled dataset of over a million regex instances with a sound filtering process to build the benchmark. We conduct extensive evaluations on 6 LLMs and 5 LRMs of varying scales, revealing common failure patterns such as verbosity and repetition. With its well-defined structure and quantitative evaluation metrics, this work presents the first empirical investigation into the spatial computational limitations of LLMs and LRMs, offering a new framework for evaluating their advanced reasoning capabilities. Our code is available at https://github.com/hyundong98/RegexPSPACE .

Causal discovery is fundamental to scientific research, yet traditional statistical algorithms face significant challenges, including expensive data collection, redundant computation for known relations, and unrealistic assumptions. While recent LLM-based methods excel at identifying commonly known causal relations, they fail to uncover novel relations. We introduce IRIS (Iterative Retrieval and Integrated System for Real-Time Causal Discovery), a novel framework that addresses these limitations. Starting with a set of initial variables, IRIS automatically collects relevant documents, extracts variables, and uncovers causal relations. Our hybrid causal discovery method combines statistical algorithms and LLM-based methods to discover known and novel causal relations. In addition to causal discovery on initial variables, the missing variable proposal component of IRIS identifies and incorporates missing variables to expand the causal graphs. Our approach enables real-time causal discovery from only a set of initial variables without requiring pre-existing datasets.

Large Language Models (LLMs) have shown remarkable success, and their multimodal expansions (MLLMs) further unlock capabilities spanning images, videos, and other modalities beyond text. However, despite this shift, prompt optimization approaches, designed to reduce the burden of manual prompt crafting while maximizing performance, remain confined to text, ultimately limiting the full potential of MLLMs. Motivated by this gap, we introduce the new problem of multimodal prompt optimization, which expands the prior definition of prompt optimization to the multimodal space defined by the pairs of textual and non-textual prompts. To tackle this problem, we then propose the Multimodal Prompt Optimizer (MPO), a unified framework that not only performs the joint optimization of multimodal prompts through alignment-preserving updates but also guides the selection process of candidate prompts by leveraging earlier evaluations as priors in a Bayesian-based selection strategy. Through extensive experiments across diverse modalities that go beyond text, such as images, videos, and even molecules, we demonstrate that MPO outperforms leading text-only optimization methods, establishing multimodal prompt optimization as a crucial step to realizing the potential of MLLMs.

General Large Language Models (LLMs) excel in reasoning, but those enhanced for translation struggle with reasoning tasks. To address this, we propose a novel translationenhanced recipe that begins with instruct models and applies layer-selective tuning only on parallel data. Following this pipeline, we introduce the Qwen3-XPlus models, which demonstrate significant improvements in translation performance across both high- and lowresource languages, achieving 15+ spBLEU and 40+ xComet in low-resource languages, like Swahili. Interestingly, training only with small parallel datasets, Qwen3-XPlus achieves an average improvement of 1+ points on 7 multilingual tasks while maintaining proficiency comparable to the Qwen3 instruct model in 15 popular reasoning datasets. This work offers a promising approach to multilingual enhancement, significantly reducing complexity and enhancing accessibility for a wider range of languages. The code and model are publicly available.

Text de-identification techniques are often used to mask personally identifiable information (PII) from documents. Their ability to conceal the identity of the individuals mentioned in a text is, however, hard to measure. Recent work has shown how the robustness of de-identification methods could be assessed by attempting the reverse process of _re-identification_, based on an automated adversary using its background knowledge to uncover the PIIs that have been masked. This paper presents two complementary strategies to build stronger re-identification attacks. We first show that (1) the _order_ in which the PII spans are re-identified matters, and that aggregating predictions across multiple orderings leads to improved results. We also find that (2) reasoning models can boost the re-identification performance, especially when the adversary is assumed to have access to extensive background knowledge.

Electronic Health Records (EHRs) enable deep learning for clinical predictions, but the optimal method for representing patient data remains unclear due to inconsistent evaluation practices. We present the first systematic benchmark to compare EHR representation methods, including multivariate time-series, event streams, and textual event streams for LLMs. This benchmark standardises data curation and evaluation across two distinct clinical settings: the MIMIC-IV dataset for ICU tasks (mortality, phenotyping) and the EHRSHOT dataset for longitudinal care (30-day readmission, 1-year pancreatic cancer). For each paradigm, we evaluate appropriate modelling families--including Transformers, MLP, LSTMs and Retain for time-series, CLMBR and count-based models for event streams, 8-20B LLMs for textual streams--and analyse the impact of feature pruning based on data missingness. Our experiments reveal that event stream models consistently deliver the strongest performance. Pre-trained models like CLMBR are highly sample-efficient in few-shot settings, though simpler count-based models can be competitive given sufficient data. Furthermore, we find that feature selection strategies must be adapted to the clinical setting: pruning sparse features improves ICU predictions, while retaining them is critical for longitudinal tasks. Our results, enabled by a unified and reproducible pipeline, provide practical guidance for selecting EHR representations based on the clinical context and data regime.