With the rapid development of Large Language Models (LLMs), numerous Reinforcement Learning from Human Feedback (RLHF) algorithms have been introduced to improve model safety and alignment with human preferences. These algorithms can be divided into two main frameworks based on whether they require an explicit reward (or value) function for training: actor-critic-based Proximal Policy Optimization (PPO) and alignment-based Direct Preference Optimization (DPO). The mismatch between DPO and PPO, such as DPO's use of a classification loss driven by human-preferred data, has raised confusion about whether DPO should be classified as a Reinforcement Learning (RL) algorithm. To address these ambiguities, we focus on three key aspects related to DPO, RL, and other RLHF algorithms: (1) the construction of the loss function; (2) the target distribution at which the algorithm converges; (3) the impact of key components within the loss function. Specifically, we first establish a unified framework named UDRRA connecting these algorithms based on the construction of their loss functions. Next, we uncover their target policy distributions within this framework. Finally, we investigate the critical components of DPO to understand their impact on the convergence rate. Our work provides a deeper understanding of the relationship between DPO, RL, and other RLHF algorithms, offering new insights for improving existing algorithms.

Accelerated MRI reconstruction techniques aim to reduce examination time while maintaining high image fidelity, which is highly desirable in clinical settings for improving patient comfort and hospital efficiency. Existing deep learning methods typically reconstruct images from under-sampled data with traditional reconstruction approaches, but they still struggle to provide high-fidelity results. Diffusion models show great potential to improve fidelity of generated images in recent years. However, their inference process starting with a random Gaussian noise introduces instability into the results and usually requires thousands of sampling steps, resulting in sub-optimal reconstruction quality and low efficiency. To address these challenges, we propose Cycle-Consistent Bridge Diffusion Model (CBDM). CBDM employs two bridge diffusion models to construct a cycle-consistent diffusion process with a consistency loss, enhancing the fine-grained details of reconstructed images and reducing the number of diffusion steps. Moreover, CBDM incorporates a Contourlet Decomposition Embedding Module (CDEM) which captures multi-scale structural texture knowledge in images through frequency domain decomposition pyramids and directional filter banks to improve structural fidelity. Extensive experiments demonstrate the superiority of our model by higher reconstruction quality and fewer training iterations, achieving a new state of the art for accelerated MRI reconstruction in both fastMRI and IXI datasets.

Previous studies have demonstrated that emotional features from a single acoustic sentiment label can enhance depression diagnosis accuracy. Additionally, according to the Emotion Context-Insensitivity theory and our pilot study, individuals with depression might convey negative emotional content in an unexpectedly calm manner, showing a high degree of inconsistency in emotional expressions during natural conversations. So far, few studies have recognized and leveraged the emotional expression inconsistency for depression detection. In this paper, a multimodal cross-attention method is presented to capture the Acoustic-Textual Emotional Inconsistency (ATEI) information. This is achieved by analyzing the intricate local and long-term dependencies of emotional expressions across acoustic and textual domains, as well as the mismatch between the emotional content within both domains. A Transformer-based model is then proposed to integrate this ATEI information with various fusion strategies for detecting depression. Furthermore, a scaling technique is employed to adjust the ATEI feature degree during the fusion process, thereby enhancing the model's ability to discern patients with depression across varying levels of severity. To best of our knowledge, this work is the first to incorporate emotional expression inconsistency information into depression detection. Experimental results on a counseling conversational dataset illustrate the effectiveness of our method.

Multimodal MR image synthesis aims to generate missing modality image by fusing and mapping a few available MRI data. Most existing approaches typically adopt an image-to-image translation scheme. However, these methods often suffer from sub-optimal performance due to the spatial misalignment between different modalities while they are typically treated as input channels. Therefore, in this paper, we propose an Adaptive Group-wise Interaction Network (AGI-Net) that explores both inter-modality and intra-modality relationships for multimodal MR image synthesis. Specifically, groups are first pre-defined along the channel dimension and then we perform an adaptive rolling for the standard convolutional kernel to capture inter-modality spatial correspondences. At the same time, a cross-group attention module is introduced to fuse information across different channel groups, leading to better feature representation. We evaluated the effectiveness of our model on the publicly available IXI and BraTS2023 datasets, where the AGI-Net achieved state-of-the-art performance for multimodal MR image synthesis.

SAR images possess unique attributes that present challenges for both human observers and vision AI models to interpret, owing to their electromagnetic characteristics. The interpretation of SAR images encounters various hurdles, with one of the primary obstacles being the data itself, which includes issues related to both the quantity and quality of the data. The challenges can be addressed using generative AI technologies. Generative AI, often known as GenAI, is a very advanced and powerful technology in the field of artificial intelligence that has gained significant attention. The advancement has created possibilities for the creation of texts, photorealistic pictures, videos, and material in various modalities. This paper aims to comprehensively investigate the intersection of GenAI and SAR. First, we illustrate the common data generation-based applications in SAR field and compare them with computer vision tasks, analyzing the similarity, difference, and general challenges of them. Then, an overview of the latest GenAI models is systematically reviewed, including various basic models and their variations targeting the general challenges. Additionally, the corresponding applications in SAR domain are also included. Specifically, we propose to summarize the physical model based simulation approaches for SAR, and analyze the hybrid modeling methods that combine the GenAI and interpretable models. The evaluation methods that have been or could be applied to SAR, are also explored. Finally, the potential challenges and future prospects are discussed. To our best knowledge, this survey is the first exhaustive examination of the interdiscipline of SAR and GenAI, encompassing a wide range of topics, including deep neural networks, physical models, computer vision, and SAR images. The resources of this survey are open-source at \url{https://github.com/XAI4SAR/GenAIxSAR}.

3D Gaussian Splatting algorithms excel in novel view rendering applications and have been adapted to extend the capabilities of traditional SLAM systems. However, current Gaussian Splatting SLAM methods, designed mainly for hand-held RGB or RGB-D sensors, struggle with tracking drifts when used with rotating RGB-D camera setups. In this paper, we propose a robust Gaussian Splatting SLAM architecture that utilizes inputs from rotating multiple RGB-D cameras to achieve accurate localization and photorealistic rendering performance. The carefully designed Gaussian Splatting Loop Closure module effectively addresses the issue of accumulated tracking and mapping errors found in conventional Gaussian Splatting SLAM systems. First, each Gaussian is associated with an anchor frame and categorized as historical or novel based on its timestamp. By rendering different types of Gaussians at the same viewpoint, the proposed loop detection strategy considers both co-visibility relationships and distinct rendering outcomes. Furthermore, a loop closure optimization approach is proposed to remove camera pose drift and maintain the high quality of 3D Gaussian models. The approach uses a lightweight pose graph optimization algorithm to correct pose drift and updates Gaussians based on the optimized poses. Additionally, a bundle adjustment scheme further refines camera poses using photometric and geometric constraints, ultimately enhancing the global consistency of scenarios. Quantitative and qualitative evaluations on both synthetic and real-world datasets demonstrate that our method outperforms state-of-the-art methods in camera pose estimation and novel view rendering tasks. The code will be open-sourced for the community.

Alphas are pivotal in providing signals for quantitative trading. The industry highly values the discovery of formulaic alphas for their interpretability and ease of analysis, compared with the expressive yet overfitting-prone black-box alphas. In this work, we focus on discovering formulaic alphas. Prior studies on automatically generating a collection of formulaic alphas were mostly based on genetic programming (GP), which is known to suffer from the problems of being sensitive to the initial population, converting to local optima, and slow computation speed. Recent efforts employing deep reinforcement learning (DRL) for alpha discovery have not fully addressed key practical considerations such as alpha correlations and validity, which are crucial for their effectiveness. In this work, we propose a novel framework for alpha discovery using DRL by formulating the alpha discovery process as program construction. Our agent, $\text{Alpha}^2$, assembles an alpha program optimized for an evaluation metric. A search algorithm guided by DRL navigates through the search space based on value estimates for potential alpha outcomes. The evaluation metric encourages both the performance and the diversity of alphas for a better final trading strategy. Our formulation of searching alphas also brings the advantage of pre-calculation dimensional analysis, ensuring the logical soundness of alphas, and pruning the vast search space to a large extent. Empirical experiments on real-world stock markets demonstrates $\text{Alpha}^2$'s capability to identify a diverse set of logical and effective alphas, which significantly improves the performance of the final trading strategy. The code of our method is available at https://github.com/x35f/alpha2.

The ability to model the underlying dynamics of visual scenes and reason about the future is central to human intelligence. Many attempts have been made to empower intelligent systems with such physical understanding and prediction abilities. However, most existing methods focus on pixel-to-pixel prediction, which suffers from heavy computational costs while lacking a deep understanding of the physical dynamics behind videos. Recently, object-centric prediction methods have emerged and attracted increasing interest. Inspired by it, this paper proposes an unsupervised object-centric prediction model that makes future predictions by learning visual dynamics between objects. Our model consists of two modules, perceptual, and dynamic module. The perceptual module is utilized to decompose images into several objects and synthesize images with a set of object-centric representations. The dynamic module fuses contextual information, takes environment-object and object-object interaction into account, and predicts the future trajectory of objects. Extensive experiments are conducted to validate the effectiveness of the proposed method. Both quantitative and qualitative experimental results demonstrate that our model generates higher visual quality and more physically reliable predictions compared to the state-of-the-art methods.

The ionosphere is a vitally dynamic charged particle region in the Earth's upper atmosphere, playing a crucial role in applications such as radio communication and satellite navigation. The Slant Total Electron Contents (STEC) is an important parameter for characterizing wave propagation, representing the integrated electron density along the ray of radio signals passing through the ionosphere. The accurate prediction of STEC is essential for mitigating the ionospheric impact particularly on Global Navigation Satellite Systems (GNSS). In this work, we propose a high-precision STEC prediction model named DeepONet-STEC, which learns nonlinear operators to predict the 4D temporal-spatial integrated parameter for specified ground station - satellite ray path globally. As a demonstration, we validate the performance of the model based on GNSS observation data for global and US-CORS regimes under ionospheric quiet and storm conditions. The DeepONet-STEC model results show that the three-day 72 hour prediction in quiet periods could achieve high accuracy using observation data by the Precise Point Positioning (PPP) with temporal resolution 30s. Under active solar magnetic storm periods, the DeepONet-STEC also demonstrated its robustness and superiority than traditional deep learning methods. This work presents a neural operator regression architecture for predicting the 4D temporal-spatial ionospheric parameter for satellite navigation system performance, which may be further extended for various space applications and beyond.

State estimation for legged robots is challenging due to their highly dynamic motion and limitations imposed by sensor accuracy. By integrating Kalman filtering, optimization, and learning-based modalities, we propose a hybrid solution that combines proprioception and exteroceptive information for estimating the state of the robot's trunk. Leveraging joint encoder and IMU measurements, our Kalman filter is enhanced through a single-rigid body model that incorporates ground reaction force control outputs from convex Model Predictive Control optimization. The estimation is further refined through Gated Recurrent Units, which also considers semantic insights and robot height from a Vision Transformer autoencoder applied on depth images. This framework not only furnishes accurate robot state estimates, including uncertainty evaluations, but can minimize the nonlinear errors that arise from sensor measurements and model simplifications through learning. The proposed methodology is evaluated in hardware using a quadruped robot on various terrains, yielding a 65% improvement on the Root Mean Squared Error compared to our VIO SLAM baseline. Code example: https://github.com/AlexS28/OptiState