VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

Most organizational data in this world are stored as documents, and visual retrieval plays a crucial role in unlocking the collective intelligence from all these documents. However, existing benchmarks focus on English-only document retrieval or only consider multilingual question-answering on a single-page image. To bridge this gap, we introduce VisR-Bench, a multilingual benchmark designed for question-driven multimodal retrieval in long documents. Our benchmark comprises over 35K high-quality QA pairs across 1.2K documents, enabling fine-grained evaluation of multimodal retrieval. VisR-Bench spans sixteen languages with three question types (figures, text, and tables), offering diverse linguistic and question coverage. Unlike prior datasets, we include queries without explicit answers, preventing models from relying on superficial keyword matching. We evaluate various retrieval models, including text-based methods, multimodal encoders, and MLLMs, providing insights into their strengths and limitations. Our results show that while MLLMs significantly outperform text-based and multimodal encoder models, they still struggle with structured tables and low-resource languages, highlighting key challenges in multilingual visual retrieval.

Arce: Augmented Roberta with Contextualized Elucidations for Ner in Automated Rule Checking

Accurate information extraction from specialized texts is a critical challenge, particularly for named entity recognition (NER) in the architecture, engineering, and construction (AEC) domain to support automated rule checking (ARC). The performance of standard pre-trained models is often constrained by the domain gap, as they struggle to interpret the specialized terminology and complex relational contexts inherent in AEC texts. Although this issue can be mitigated by further pre-training on large, human-curated domain corpora, as exemplified by methods like ARCBERT, this approach is both labor-intensive and cost-prohibitive. Consequently, leveraging large language models (LLMs) for automated knowledge generation has emerged as a promising alternative. However, the optimal strategy for generating knowledge that can genuinely enhance smaller, efficient models remains an open question. To address this, we propose ARCE (augmented RoBERTa with contextualized elucidations), a novel approach that systematically explores and optimizes this generation process. ARCE employs an LLM to first generate a corpus of simple, direct explanations, which we term Cote, and then uses this corpus to incrementally pre-train a RoBERTa model prior to its fine-tuning on the downstream task. Our extensive experiments show that ARCE establishes a new state-of-the-art on a benchmark AEC dataset, achieving a Macro-F1 score of 77.20%. This result also reveals a key finding: simple, explanation-based knowledge proves surprisingly more effective than complex, role-based rationales for this task. The code is publicly available at:https://github.com/nxcc-lab/ARCE.

Exploring Audio Cues for Enhanced Test-Time Video Model Adaptation

Test-time adaptation (TTA) aims to boost the generalization capability of a trained model by conducting self-/unsupervised learning during the testing phase. While most existing TTA methods for video primarily utilize visual supervisory signals, they often overlook the potential contribution of inherent audio data. To address this gap, we propose a novel approach that incorporates audio information into video TTA. Our method capitalizes on the rich semantic content of audio to generate audio-assisted pseudo-labels, a new concept in the context of video TTA. Specifically, we propose an audio-to-video label mapping method by first employing pre-trained audio models to classify audio signals extracted from videos and then mapping the audio-based predictions to video label spaces through large language models, thereby establishing a connection between the audio categories and video labels. To effectively leverage the generated pseudo-labels, we present a flexible adaptation cycle that determines the optimal number of adaptation iterations for each sample, based on changes in loss and consistency across different views. This enables a customized adaptation process for each sample. Experimental results on two widely used datasets (UCF101-C and Kinetics-Sounds-C), as well as on two newly constructed audio-video TTA datasets (AVE-C and AVMIT-C) with various corruption types, demonstrate the superiority of our approach. Our method consistently improves adaptation performance across different video classification models and represents a significant step forward in integrating audio information into video TTA. Code: https://github.com/keikeiqi/Audio-Assisted-TTA.

FastFLUX: Pruning FLUX with Block-wise Replacement and Sandwich Training

Recent advancements in text-to-image (T2I) generation have led to the emergence of highly expressive models such as diffusion transformers (DiTs), exemplified by FLUX. However, their massive parameter sizes lead to slow inference, high memory usage, and poor deployability. Existing acceleration methods (e.g., single-step distillation and attention pruning) often suffer from significant performance degradation and incur substantial training costs. To address these limitations, we propose FastFLUX, an architecture-level pruning framework designed to enhance the inference efficiency of FLUX. At its core is the Block-wise Replacement with Linear Layers (BRLL) method, which replaces structurally complex residual branches in ResBlocks with lightweight linear layers while preserving the original shortcut connections for stability. Furthermore, we introduce Sandwich Training (ST), a localized fine-tuning strategy that leverages LoRA to supervise neighboring blocks, mitigating performance drops caused by structural replacement. Experiments show that our FastFLUX maintains high image quality under both qualitative and quantitative evaluations, while significantly improving inference speed, even with 20\% of the hierarchy pruned. Our code will be available soon.

Rectified Sparse Attention

Efficient long-sequence generation is a critical challenge for Large Language Models. While recent sparse decoding methods improve efficiency, they suffer from KV cache misalignment, where approximation errors accumulate and degrade generation quality. In this work, we propose Rectified Sparse Attention (ReSA), a simple yet effective method that combines block-sparse attention with periodic dense rectification. By refreshing the KV cache at fixed intervals using a dense forward pass, ReSA bounds error accumulation and preserves alignment with the pretraining distribution. Experiments across math reasoning, language modeling, and retrieval tasks demonstrate that ReSA achieves near-lossless generation quality with significantly improved efficiency. Notably, ReSA delivers up to 2.42$\times$ end-to-end speedup under decoding at 256K sequence length, making it a practical solution for scalable long-context inference. Code is available at https://aka.ms/ReSA-LM.

Interpreting Chest X-rays Like a Radiologist: A Benchmark with Clinical Reasoning

Artificial intelligence (AI)-based chest X-ray (CXR) interpretation assistants have demonstrated significant progress and are increasingly being applied in clinical settings. However, contemporary medical AI models often adhere to a simplistic input-to-output paradigm, directly processing an image and an instruction to generate a result, where the instructions may be integral to the model's architecture. This approach overlooks the modeling of the inherent diagnostic reasoning in chest X-ray interpretation. Such reasoning is typically sequential, where each interpretive stage considers the images, the current task, and the contextual information from previous stages. This oversight leads to several shortcomings, including misalignment with clinical scenarios, contextless reasoning, and untraceable errors. To fill this gap, we construct CXRTrek, a new multi-stage visual question answering (VQA) dataset for CXR interpretation. The dataset is designed to explicitly simulate the diagnostic reasoning process employed by radiologists in real-world clinical settings for the first time. CXRTrek covers 8 sequential diagnostic stages, comprising 428,966 samples and over 11 million question-answer (Q&A) pairs, with an average of 26.29 Q&A pairs per sample. Building on the CXRTrek dataset, we propose a new vision-language large model (VLLM), CXRTrekNet, specifically designed to incorporate the clinical reasoning flow into the VLLM framework. CXRTrekNet effectively models the dependencies between diagnostic stages and captures reasoning patterns within the radiological context. Trained on our dataset, the model consistently outperforms existing medical VLLMs on the CXRTrek benchmarks and demonstrates superior generalization across multiple tasks on five diverse external datasets. The dataset and model can be found in our repository (https://github.com/guanjinquan/CXRTrek).

Compliance-to-Code: Enhancing Financial Compliance Checking via Code Generation

Nowadays, regulatory compliance has become a cornerstone of corporate governance, ensuring adherence to systematic legal frameworks. At its core, financial regulations often comprise highly intricate provisions, layered logical structures, and numerous exceptions, which inevitably result in labor-intensive or comprehension challenges. To mitigate this, recent Regulatory Technology (RegTech) and Large Language Models (LLMs) have gained significant attention in automating the conversion of regulatory text into executable compliance logic. However, their performance remains suboptimal particularly when applied to Chinese-language financial regulations, due to three key limitations: (1) incomplete domain-specific knowledge representation, (2) insufficient hierarchical reasoning capabilities, and (3) failure to maintain temporal and logical coherence. One promising solution is to develop a domain specific and code-oriented datasets for model training. Existing datasets such as LexGLUE, LegalBench, and CODE-ACCORD are often English-focused, domain-mismatched, or lack fine-grained granularity for compliance code generation. To fill these gaps, we present Compliance-to-Code, the first large-scale Chinese dataset dedicated to financial regulatory compliance. Covering 1,159 annotated clauses from 361 regulations across ten categories, each clause is modularly structured with four logical elements-subject, condition, constraint, and contextual information-along with regulation relations. We provide deterministic Python code mappings, detailed code reasoning, and code explanations to facilitate automated auditing. To demonstrate utility, we present FinCheck: a pipeline for regulation structuring, code generation, and report generation.

TopicVD: A Topic-Based Dataset of Video-Guided Multimodal Machine Translation for Documentaries

Most existing multimodal machine translation (MMT) datasets are predominantly composed of static images or short video clips, lacking extensive video data across diverse domains and topics. As a result, they fail to meet the demands of real-world MMT tasks, such as documentary translation. In this study, we developed TopicVD, a topic-based dataset for video-supported multimodal machine translation of documentaries, aiming to advance research in this field. We collected video-subtitle pairs from documentaries and categorized them into eight topics, such as economy and nature, to facilitate research on domain adaptation in video-guided MMT. Additionally, we preserved their contextual information to support research on leveraging the global context of documentaries in video-guided MMT. To better capture the shared semantics between text and video, we propose an MMT model based on a cross-modal bidirectional attention module. Extensive experiments on the TopicVD dataset demonstrate that visual information consistently improves the performance of the NMT model in documentary translation. However, the MMT model's performance significantly declines in out-of-domain scenarios, highlighting the need for effective domain adaptation methods. Additionally, experiments demonstrate that global context can effectively improve translation performance. % Dataset and our implementations are available at https://github.com/JinzeLv/TopicVD

BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese

As large language models (LLMs) evolve into tool-using agents, the ability to browse the web in real-time has become a critical yardstick for measuring their reasoning and retrieval competence. Existing benchmarks such as BrowseComp concentrate on English and overlook the linguistic, infrastructural, and censorship-related complexities of other major information ecosystems -- most notably Chinese. To address this gap, we introduce BrowseComp-ZH, a high-difficulty benchmark purpose-built to comprehensively evaluate LLM agents on the Chinese web. BrowseComp-ZH consists of 289 multi-hop questions spanning 11 diverse domains. Each question is reverse-engineered from a short, objective, and easily verifiable answer (e.g., a date, number, or proper noun). A two-stage quality control protocol is applied to strive for high question difficulty and answer uniqueness. We benchmark over 20 state-of-the-art language models and agentic search systems on our proposed BrowseComp-ZH. Despite their strong conversational and retrieval capabilities, most models struggle severely: a large number achieve accuracy rates below 10%, and only a handful exceed 20%. Even the best-performing system, OpenAI's DeepResearch, reaches just 42.9%. These results demonstrate the considerable difficulty of BrowseComp-ZH, where success demands not only effective retrieval strategies, but also sophisticated reasoning and information reconciliation -- capabilities that current models still struggle to master. Our dataset, construction guidelines, and benchmark results have been publicly released at https://github.com/PALIN2018/BrowseComp-ZH.

Towards Visual Text Grounding of Multimodal Large Language Model

Despite the existing evolution of Multimodal Large Language Models (MLLMs), a non-neglectable limitation remains in their struggle with visual text grounding, especially in text-rich images of documents. Document images, such as scanned forms and infographics, highlight critical challenges due to their complex layouts and textual content. However, current benchmarks do not fully address these challenges, as they mostly focus on visual grounding on natural images, rather than text-rich document images. Thus, to bridge this gap, we introduce TRIG, a novel task with a newly designed instruction dataset for benchmarking and improving the Text-Rich Image Grounding capabilities of MLLMs in document question-answering. Specifically, we propose an OCR-LLM-human interaction pipeline to create 800 manually annotated question-answer pairs as a benchmark and a large-scale training set of 90$ synthetic data based on four diverse datasets. A comprehensive evaluation of various MLLMs on our proposed benchmark exposes substantial limitations in their grounding capability on text-rich images. In addition, we propose two simple and effective TRIG methods based on general instruction tuning and plug-and-play efficient embedding, respectively. By finetuning MLLMs on our synthetic dataset, they promisingly improve spatial reasoning and grounding capabilities.