This paper introduces Light-R1, an open-source suite for training long reasoning models using reproducible and cost-effective methodology. Given the proprietary nature of data used in the DeepSeek-R1 series, we develop an alternative approach leveraging exclusively public data and models. Our curriculum training progressively increases data difficulty, combined with multi-staged post-training. Our Light-R1-32B model, trained from Qwen2.5-32B-Instruct, outperforms DeepSeek-R1-Distill-Qwen-32B in math reasoning. Experimental results show that this curriculum approach becomes more effective when distinct, diverse datasets are available for different training stages: fine-tuning DeepSeek-R1-Distilled models (pre-tuned by DeepSeek team on proprietary data) with 3,000 challenging examples from our curriculum dataset yielded state-of-the-art 7B and 14B models, while the 32B model, Light-R1-32B-DS performed comparably to QwQ-32B and DeepSeek-R1. Furthermore, we extend our work by applying GRPO on long reasoning models. Our final Light-R1-14B-DS achieves SOTA performance among 14B models in math, with AIME24 \& 25 scores of 74.0 and 60.2 respectively, surpassing many 32B models and DeepSeek-R1-Distill-Llama-70B. Despite math-focused training, Light-R1-14B-DS demonstrates strong cross-domain generalization. Light-R1 represents a significant advancement in making sophisticated reasoning models more accessible and implementable in real-world applications. Our models, training data and code have been made available at https://github.com/Qihoo360/Light-R1.

Transformer-based large language models (LLMs) have demonstrated exceptional capabilities in sequence modeling and text generation, with improvements scaling proportionally with model size. However, the limitations of GPU memory have restricted LLM training accessibility for many researchers. Existing heterogeneous training methods significantly expand the scale of trainable models but introduce substantial communication overheads and CPU workloads. In this work, we propose AutoHete, an automatic and efficient heterogeneous training system compatible with both single-GPU and multi-GPU environments. AutoHete dynamically adjusts activation checkpointing, parameter offloading, and optimizer offloading based on the specific hardware configuration and LLM training needs. Additionally, we design a priority-based scheduling mechanism that maximizes the overlap between operations across training iterations, enhancing throughput. Compared to state-of-the-art heterogeneous training systems, AutoHete delivers a 1.32x~1.91x throughput improvement across various model sizes and training configurations.

Estimating the mean-variance efficient (MVE) frontier is crucial for asset pricing and investment management. Yet, estimating the tangency portfolio (Markowitz, 1952) using the unbalanced panel of thousands of individual asset returns proves impracticable. Empirical studies typically consider a "diversified" set of test assets (e.g., ME-BM 25 portfolios) to estimate and evaluate factor models, hoping these test assets or a few common factors can span the same efficient frontier as individual assets. However, popular factor models hardly explain the cross section of conventional prespecified test assets (e.g., Kozak et al., 2018; Lopez-Lira and Roussanov, 2020), not to mention the ad hoc nature of these test assets hampers the effectiveness of model estimations and evaluations (Lewellen et al., 2010; Ang et al., 2020). For example, characteristics-based test assets are often limited to univariate-and bivariate-sorted portfolios due to the challenges of high-dimensional sorting (Cochrane, 2011), overlooking nonlinearity and asymmetric interactions (that do not uniformly apply to all assets), even with dependent sorting (Daniel et al., 1997).

Graph Neural Networks (GNNs) have shown great success in various graph-based learning tasks. However, it often faces the issue of over-smoothing as the model depth increases, which causes all node representations to converge to a single value and become indistinguishable. This issue stems from the inherent limitations of GNNs, which struggle to distinguish the importance of information from different neighborhoods. In this paper, we introduce MbaGCN, a novel graph convolutional architecture that draws inspiration from the Mamba paradigm-originally designed for sequence modeling. MbaGCN presents a new backbone for GNNs, consisting of three key components: the Message Aggregation Layer, the Selective State Space Transition Layer, and the Node State Prediction Layer. These components work in tandem to adaptively aggregate neighborhood information, providing greater flexibility and scalability for deep GNN models. While MbaGCN may not consistently outperform all existing methods on each dataset, it provides a foundational framework that demonstrates the effective integration of the Mamba paradigm into graph representation learning. Through extensive experiments on benchmark datasets, we demonstrate that MbaGCN paves the way for future advancements in graph neural network research.

Graph Neural Networks (GNNs) demonstrate significant potential in various applications but remain highly vulnerable to adversarial attacks, which can greatly degrade their performance. Existing graph purification methods attempt to address this issue by filtering attacked graphs; however, they struggle to effectively defend against multiple types of adversarial attacks simultaneously due to their limited flexibility, and they lack comprehensive modeling of graph data due to their heavy reliance on heuristic prior knowledge. To overcome these challenges, we propose a more versatile approach for defending against adversarial attacks on graphs. In this work, we introduce the Graph Defense Diffusion Model (GDDM), a flexible purification method that leverages the denoising and modeling capabilities of diffusion models. The iterative nature of diffusion models aligns well with the stepwise process of adversarial attacks, making them particularly suitable for defense. By iteratively adding and removing noise, GDDM effectively purifies attacked graphs, restoring their original structure and features. Our GDDM consists of two key components: (1) Graph Structure-Driven Refiner, which preserves the basic fidelity of the graph during the denoising process, and ensures that the generated graph remains consistent with the original scope; and (2) Node Feature-Constrained Regularizer, which removes residual impurities from the denoised graph, further enhances the purification effect. Additionally, we design tailored denoising strategies to handle different types of adversarial attacks, improving the model's adaptability to various attack scenarios. Extensive experiments conducted on three real-world datasets demonstrate that GDDM outperforms state-of-the-art methods in defending against a wide range of adversarial attacks, showcasing its robustness and effectiveness.

The multimodal language models (MLMs) based on generative pre-trained Transformer are considered powerful candidates for unifying various domains and tasks. MLMs developed for remote sensing (RS) have demonstrated outstanding performance in multiple tasks, such as visual question answering and visual grounding. In addition to visual grounding that detects specific objects corresponded to given instruction, aerial detection, which detects all objects of multiple categories, is also a valuable and challenging task for RS foundation models. However, aerial detection has not been explored by existing RS MLMs because the autoregressive prediction mechanism of MLMs differs significantly from the detection outputs. In this paper, we present a simple baseline for applying MLMs to aerial detection for the first time, named LMMRotate. Specifically, we first introduce a normalization method to transform detection outputs into textual outputs to be compatible with the MLM framework. Then, we propose a evaluation method, which ensures a fair comparison between MLMs and conventional object detection models. We construct the baseline by fine-tuning open-source general-purpose MLMs and achieve impressive detection performance comparable to conventional detector. We hope that this baseline will serve as a reference for future MLM development, enabling more comprehensive capabilities for understanding RS images. Code is available at https://github.com/Li-Qingyun/mllm-mmrotate.

In recent years, researchers have attempted to exploit social relations to improve the performance in recommendation systems. Generally, most existing social recommendation methods heavily depends on substantial domain knowledge and expertise in primary recommendation tasks for designing useful auxiliary tasks. Meanwhile, Self-Supervised Learning (SSL) recently has received considerable attention in the field of recommendation, since it can provide self-supervision signals in assisting the improvement of target recommendation systems by constructing self-supervised auxiliary tasks from raw data without human-annotated labels. Despite the great success, these SSL-based social recommendations are insufficient to adaptively balance various self-supervised auxiliary tasks, since assigning equal weights on various auxiliary tasks can result in sub-optimal recommendation performance, where different self-supervised auxiliary tasks may contribute differently to improving the primary social recommendation across different datasets. To address this issue, in this work, we propose Adaptive Self-supervised Learning for Social Recommendations (AdasRec) by taking advantage of various self-supervised auxiliary tasks. More specifically, an adaptive weighting mechanism is proposed to learn adaptive weights for various self-supervised auxiliary tasks, so as to balance the contribution of such self-supervised auxiliary tasks for enhancing representation learning in social recommendations. The adaptive weighting mechanism is used to assign different weights on auxiliary tasks to achieve an overall weighting of the entire auxiliary tasks and ultimately assist the primary recommendation task, achieved by a meta learning optimization problem with an adaptive weighting network. Comprehensive experiments on various real-world datasets are constructed to verify the effectiveness of our proposed method.

Abstract-- Poor sitting posture can lead to various work-related musculoskeletal disorders (WMSDs). Office employees spend approximately 81.8% of their working time seated, and sedentary behavior can result in chronic diseases such as cervical spondylosis and cardiovascular diseases. Our results show that the ensemble learning model based on the soft voting mechanism achieves the highest F1 score of 98.1%. Finally, we deployed the SitPose system based on this ensemble model to encourage better sitting posture and to reduce sedentary habits. Office workers typically remain seated throughout their provided insights into the health implications of prolonged workday due to the nature of their tasks and various other sedentary lifestyles. Consequently, many experience backaches, primarily cohort of 360,047 participants from the UK Biobank, delved due to their poor sitting posture and prolonged sedentary into the relationship between sedentary behavior (exceeding 6 habits. Furthermore, prolonged sitting can aims to mitigate such risks by introducing a novel double the risk of developing diabetes, as well as contribute to sitting posture health detection system that utilizes visual the accumulation of abdominal fat, leading to health problems detection technology to provide interactive reminders. The RoSeFi [5] system between increased durations of sedentary behavior in adopted WiFi channel state information to monitor sedentary the workplace and a decline in self-reported general health status.

In recent years, as the population ages, falls have increasingly posed a significant threat to the health of the elderly. We propose a real-time fall detection system that integrates the inertial measurement unit (IMU) of a smartphone with optimized Wi-Fi channel state information (CSI) for secondary validation. Initially, the IMU distinguishes falls from routine daily activities with minimal computational demand. Subsequently, the CSI is employed for further assessment, which includes evaluating the individual's post-fall mobility. This methodology not only achieves high accuracy but also reduces energy consumption in the smartphone platform. An Android application developed specifically for the purpose issues an emergency alert if the user experiences a fall and is unable to move. Experimental results indicate that the CSI model, based on convolutional neural networks (CNN), achieves a detection accuracy of 99%, \revised{surpassing comparable IMU-only models, and demonstrating significant resilience in distinguishing between falls and non-fall activities.

Sparse Mixture of Experts (MoE) models, while outperforming dense Large Language Models (LLMs) in terms of performance, face significant deployment challenges during inference due to their high memory demands. Existing offloading techniques, which involve swapping activated and idle experts between the GPU and CPU, often suffer from rigid expert caching mechanisms. These mechanisms fail to adapt to dynamic routing, leading to inefficient cache utilization, or incur prohibitive costs for prediction training. To tackle these inference-specific challenges, we introduce ExpertFlow, a comprehensive system specifically designed to enhance inference efficiency by accommodating flexible routing and enabling efficient expert scheduling between CPU and GPU. This reduces overhead and boosts system performance. Central to our approach is a predictive routing path-based offloading mechanism that utilizes a lightweight predictor to accurately forecast routing paths before computation begins. This proactive strategy allows for real-time error correction in expert caching, significantly increasing cache hit ratios and reducing the frequency of expert transfers, thereby minimizing I/O overhead. Additionally, we implement a dynamic token scheduling strategy that optimizes MoE inference by rearranging input tokens across different batches. This method not only reduces the number of activated experts per batch but also improves computational efficiency. Our extensive experiments demonstrate that ExpertFlow achieves up to 93.72\% GPU memory savings and enhances inference speed by 2 to 10 times compared to baseline methods, highlighting its effectiveness and utility as a robust solution for resource-constrained inference scenarios.