Efficient vision-language understanding of large Remote Sensing Images (RSIs) is meaningful but challenging. Current Large Vision-Language Models (LVLMs) typically employ limited pre-defined grids to process images, leading to information loss when handling gigapixel RSIs. Conversely, using unlimited grids significantly increases computational costs. To preserve image details while reducing computational complexity, we propose a text-guided token pruning method with Dynamic Image Pyramid (DIP) integration. Our method introduces: (i) a Region Focus Module (RFM) that leverages text-aware region localization capability to identify critical vision tokens, and (ii) a coarse-to-fine image tile selection and vision token pruning strategy based on DIP, which is guided by RFM outputs and avoids directly processing the entire large imagery. Additionally, existing benchmarks for evaluating LVLMs' perception ability on large RSI suffer from limited question diversity and constrained image sizes. We construct a new benchmark named LRS-VQA, which contains 7,333 QA pairs across 8 categories, with image length up to 27,328 pixels. Our method outperforms existing high-resolution strategies on four datasets using the same data. Moreover, compared to existing token reduction methods, our approach demonstrates higher efficiency under high-resolution settings. Dataset and code are in https://github.com/VisionXLab/LRS-VQA.

With the continued migration of storage to cloud database systems,the impact of slow queries in such systems on services and user experience is increasing. Root-cause diagnosis plays an indispensable role in facilitating slow-query detection and revision. This paper proposes a method capable of both identifying possible root cause types for slow queries and ranking these according to their potential for accelerating slow queries. This enables prioritizing root causes with the highest impact, in turn improving slow-query revision effectiveness. To enable more accurate and detailed diagnoses, we propose the multimodal Ranking for the Root Causes of slow queries (RCRank) framework, which formulates root cause analysis as a multimodal machine learning problem and leverages multimodal information from query statements, execution plans, execution logs, and key performance indicators. To obtain expressive embeddings from its heterogeneous multimodal input, RCRank integrates self-supervised pre-training that enhances cross-modal alignment and task relevance. Next, the framework integrates root-cause-adaptive cross Transformers that enable adaptive fusion of multimodal features with varying characteristics. Finally, the framework offers a unified model that features an impact-aware training objective for identifying and ranking root causes. We report on experiments on real and synthetic datasets, finding that RCRank is capable of consistently outperforming the state-of-the-art methods at root cause identification and ranking according to a range of metrics.

Recent advances in transformer-based Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their quadratic computational complexity concerning sequence length remains a significant bottleneck for processing long documents. As a result, many efforts like sparse attention and state space models have been proposed to improve the efficiency of LLMs over long sequences. Though effective, these approaches compromise the performance or introduce structural complexity. This calls for a simple yet efficient model that preserves the fundamental Transformer architecture. To this end, we introduce SWAT, which enables efficient long-context handling via Sliding Window Attention Training. This paper first attributes the inefficiency of Transformers to the attention sink phenomenon resulting from the high variance of softmax operation. Then, we replace softmax with the sigmoid function and utilize a balanced ALiBi and Rotary Position Embedding for efficient information compression and retention. Experiments demonstrate that SWAT achieves SOTA performance compared with state-of-the-art linear recurrent architectures on eight benchmarks. Code is available at https://anonymous.4open.science/r/SWAT-attention.

Achieving human-level intelligence requires refining the transition from the fast, intuitive System 1 to the slower, more deliberate System 2 reasoning. While System 1 excels in quick, heuristic decisions, System 2 relies on logical reasoning for more accurate judgments and reduced biases. Foundational Large Language Models (LLMs) excel at fast decision-making but lack the depth for complex reasoning, as they have not yet fully embraced the step-by-step analysis characteristic of true System 2 thinking. Recently, reasoning LLMs like OpenAI's o1/o3 and DeepSeek's R1 have demonstrated expert-level performance in fields such as mathematics and coding, closely mimicking the deliberate reasoning of System 2 and showcasing human-like cognitive abilities. This survey begins with a brief overview of the progress in foundational LLMs and the early development of System 2 technologies, exploring how their combination has paved the way for reasoning LLMs. Next, we discuss how to construct reasoning LLMs, analyzing their features, the core methods enabling advanced reasoning, and the evolution of various reasoning LLMs. Additionally, we provide an overview of reasoning benchmarks, offering an in-depth comparison of the performance of representative reasoning LLMs. Finally, we explore promising directions for advancing reasoning LLMs and maintain a real-time \href{https://github.com/zzli2022/Awesome-Slow-Reason-System}{GitHub Repository} to track the latest developments. We hope this survey will serve as a valuable resource to inspire innovation and drive progress in this rapidly evolving field.

Transformers serve as the foundational architecture for many successful large-scale models, demonstrating the ability to overfit the training data while maintaining strong generalization on unseen data, a phenomenon known as benign overfitting. However, research on how the training dynamics influence error bounds within the context of benign overfitting has been limited. This paper addresses this gap by developing a generalization theory for a two-layer transformer with labeled flip noise. Specifically, we present generalization error bounds for both benign and harmful overfitting under varying signal-to-noise ratios (SNR), where the training dynamics are categorized into three distinct stages, each with its corresponding error bounds. Additionally, we conduct extensive experiments to identify key factors that influence test errors in transformers. Our experimental results align closely with the theoretical predictions, validating our findings.

Can scaling transform reasoning? In this work, we explore the untapped potential of scaling Long Chain-of-Thought (Long-CoT) data to 1000k samples, pioneering the development of a slow-thinking model, RedStar. Through extensive experiments with various LLMs and different sizes, we uncover the ingredients for specialization and scale for Long-CoT training. Surprisingly, even smaller models show significant performance gains with limited data, revealing the sample efficiency of Long-CoT and the critical role of sample difficulty in the learning process. Our findings demonstrate that Long-CoT reasoning can be effectively triggered with just a few thousand examples, while larger models achieve unparalleled improvements. We also introduce reinforcement learning (RL)-scale training as a promising direction for advancing slow-thinking systems. RedStar shines across domains: on the MATH-Hard benchmark, RedStar-code-math boosts performance from 66.2\% to 81.6\%, and on the USA Math Olympiad (AIME), it solves 46.7\% of problems using only 21k mixed-code-math datasets. In multimodal tasks like GeoQA and MathVista-GEO, RedStar-Geo achieves competitive results with minimal Long-CoT data, outperforming other slow-thinking systems like QvQ-Preview. Compared to QwQ, RedStar strikes the perfect balance between reasoning and generalizability. Our work highlights that, with careful tuning, scaling Long-CoT can unlock extraordinary reasoning capabilities-even with limited dataset and set a new standard for slow-thinking models across diverse challenges. Our data and models are released at https://huggingface.co/RedStar-Reasoning.

Multi-span answer extraction, also known as the task of multi-span question answering (MSQA), is critical for real-world applications, as it requires extracting multiple pieces of information from a text to answer complex questions. Despite the active studies and rapid progress in English MSQA research, there is a notable lack of publicly available MSQA benchmark in Chinese. Previous efforts for constructing MSQA datasets predominantly emphasized entity-centric contextualization, resulting in a bias towards collecting factoid questions and potentially overlooking questions requiring more detailed descriptive responses. To overcome these limitations, we present CLEAN, a comprehensive Chinese multi-span question answering dataset that involves a wide range of open-domain subjects with a substantial number of instances requiring descriptive answers. Additionally, we provide established models from relevant literature as baselines for CLEAN. Experimental results and analysis show the characteristics and challenge of the newly proposed CLEAN dataset for the community. Our dataset, CLEAN, will be publicly released at zhiyiluo.site/misc/clean_v1.0_ sample.json.

Urban area-of-interest (AOI) refers to an integrated urban functional zone with defined polygonal boundaries. The rapid development of urban commerce has led to increasing demands for highly accurate and timely AOI data. However, existing research primarily focuses on coarse-grained functional zones for urban planning or regional economic analysis, and often neglects the expiration of AOI in the real world. They fail to fulfill the precision demands of Mobile Internet Online-to-Offline (O2O) businesses. These businesses require accuracy down to a specific community, school, or hospital. In this paper, we propose a comprehensive end-to-end multimodal deep learning framework designed for simultaneously detecting accurate AOI boundaries and validating the reliability of AOI by leveraging remote sensing imagery coupled with geographical prior, titled AOITR. Unlike conventional AOI generation methods, such as the Road-cut method that segments road networks at various levels, our approach diverges from semantic segmentation algorithms that depend on pixel-level classification. Instead, our AOITR begins by selecting a point-of-interest (POI) of specific category, and uses it to retrieve corresponding remote sensing imagery and geographical prior such as entrance POIs and road nodes. This information helps to build a multimodal detection model based on transformer encoder-decoder architecture to regress the AOI polygon. Additionally, we utilize the dynamic features from human mobility, nearby POIs, and logistics addresses for AOI reliability evaluation via a cascaded network module. The experimental results reveal that our algorithm achieves a significant improvement on Intersection over Union (IoU) metric, surpassing previous methods by a large margin.

Transformer-based models have achieved some success in time series forecasting. Existing methods mainly model time series from limited or fixed scales, making it challenging to capture different characteristics spanning various scales. In this paper, we propose multi-scale transformers with adaptive pathways (Pathformer). The proposed Transformer integrates both temporal resolution and temporal distance for multi-scale modeling. Multi-scale division divides the time series into different temporal resolutions using patches of various sizes. Based on the division of each scale, dual attention is performed over these patches to capture global correlations and local details as temporal dependencies. We further enrich the multi-scale transformer with adaptive pathways, which adaptively adjust the multi-scale modeling process based on the varying temporal dynamics in the input time series, improving the prediction accuracy and generalization of Pathformer. Extensive experiments on eleven real-world datasets demonstrate that Pathformer not only achieves state-of-the-art performance by surpassing all current models but also exhibits stronger generalization abilities under various transfer scenarios. Time series forecasting is an essential task for various industries, such as energy, finance, traffic, and cloud computing (Chen et al., 2012; Cirstea et al., 2022b; Qin et al., 2023; Pan et al., 2023). Motivated by its widespread application in sequence modeling and impressive success in various fields such as CV and NLP (Dosovitskiy et al., 2021; Brown et al., 2020), Transformer (Vaswani et al., 2017) receives emerging attention in time series (Wu et al., 2021; Liu et al., 2022c).

$\textbf{Objectives}$: Large Language Models (LLMs) such as ChatGPT and Med-PaLM have excelled in various medical question-answering tasks. However, these English-centric models encounter challenges in non-English clinical settings, primarily due to limited clinical knowledge in respective languages, a consequence of imbalanced training corpora. We systematically evaluate LLMs in the Chinese medical context and develop a novel in-context learning framework to enhance their performance. $\textbf{Materials and Methods}$: The latest China National Medical Licensing Examination (CNMLE-2022) served as the benchmark. We collected 53 medical books and 381,149 medical questions to construct the medical knowledge base and question bank. The proposed Knowledge and Few-shot Enhancement In-context Learning (KFE) framework leverages the in-context learning ability of LLMs to integrate diverse external clinical knowledge sources. We evaluated KFE with ChatGPT(GPT3.5), GPT4, Baichuan2(BC2)-7B, and BC2-13B in CNMLE-2022 and investigated the effectiveness of different pathways for incorporating LLMs with medical knowledge from 7 perspectives. $\textbf{Results}$: Directly applying ChatGPT failed to qualify for the CNMLE-2022 at a score of 51. Cooperated with the KFE, the LLMs with varying sizes yielded consistent and significant improvements. The ChatGPT's performance surged to 70.04 and GPT-4 achieved the highest score of 82.59. This surpasses the qualification threshold (60) and exceeds the average human score of 68.70. It also enabled a smaller BC2-13B to pass the examination, showcasing the great potential in low-resource settings. $\textbf{Conclusion}$: By synergizing medical knowledge through in-context learning, LLM can extend clinical insight beyond language barriers, significantly reducing language-related disparities of LLM applications and ensuring global benefit in healthcare.