Jiasheng Wang

Yuhang Liu, Zeyu Liu, Shuanghe Zhu et al.

The emergence of Multimodal Large Language Models (MLLMs) has propelled the development of autonomous agents that operate on Graphical User Interfaces (GUIs) using pure visual input. A fundamental challenge is robustly grounding natural language instructions. This requires a precise spatial alignment, which accurately locates the coordinates of each element, and, more critically, a correct semantic alignment, which matches the instructions to the functionally appropriate UI element. Although Reinforcement Learning with Verifiable Rewards (RLVR) has proven to be effective at improving spatial alignment for these MLLMs, we find that inefficient exploration bottlenecks semantic alignment, which prevent models from learning difficult semantic associations. To address this exploration problem, we present Adaptive Exploration Policy Optimization (AEPO), a new policy optimization framework. AEPO employs a multi-answer generation strategy to enforce broader exploration, which is then guided by a theoretically grounded Adaptive Exploration Reward (AER) function derived from first principles of efficiency eta=U/C. Our AEPO-trained models, InfiGUI-G1-3B and InfiGUI-G1-7B, establish new state-of-the-art results across multiple challenging GUI grounding benchmarks, achieving significant relative improvements of up to 9.0% against the naive RLVR baseline on benchmarks designed to test generalization and semantic understanding. Resources are available at https://github.com/InfiXAI/InfiGUI-G1.

Jiasheng Wang

This paper presents a framework for learning player embeddings in competitive games and events. Players and their win-loss relationships are modeled as a skill gap graph, which is an undirected weighted graph. The player embeddings are learned from the graph using a random walk-based graph embedding method and can reflect the relative skill levels among players. Embeddings are low-dimensional vector representations that can be conveniently applied to subsequent tasks while still preserving the topological relationships in a graph. In the latter part of this paper, Graphical Elo (GElo) is introduced as an application of player embeddings when rating player skills. GElo is an extension of the classic Elo rating system. It constructs a skill gap graph based on player match histories and learns player embeddings from it. Afterward, the rating scores that were calculated by Elo are adjusted according to player activeness and cosine similarities among player embeddings. GElo can be executed offline and in parallel, and it is non-intrusive to existing rating systems. Experiments on public datasets show that GElo makes a more reliable evaluation of player skill levels than vanilla Elo. The experimental results suggest potential applications of player embeddings in competitive games and events.

Haodi Jiang, Ju Jing, Jiasheng Wang et al.

We present a new deep learning method, dubbed FibrilNet, for tracing chromospheric fibrils in Halpha images of solar observations. Our method consists of a data pre-processing component that prepares training data from a threshold-based tool, a deep learning model implemented as a Bayesian convolutional neural network for probabilistic image segmentation with uncertainty quantification to predict fibrils, and a post-processing component containing a fibril-fitting algorithm to determine fibril orientations. The FibrilNet tool is applied to high-resolution Halpha images from an active region (AR 12665) collected by the 1.6 m Goode Solar Telescope (GST) equipped with high-order adaptive optics at the Big Bear Solar Observatory (BBSO). We quantitatively assess the FibrilNet tool, comparing its image segmentation algorithm and fibril-fitting algorithm with those employed by the threshold-based tool. Our experimental results and major findings are summarized as follows. First, the image segmentation results (i.e., detected fibrils) of the two tools are quite similar, demonstrating the good learning capability of FibrilNet. Second, FibrilNet finds more accurate and smoother fibril orientation angles than the threshold-based tool. Third, FibrilNet is faster than the threshold-based tool and the uncertainty maps produced by FibrilNet not only provide a quantitative way to measure the confidence on each detected fibril, but also help identify fibril structures that are not detected by the threshold-based tool but are inferred through machine learning. Finally, we apply FibrilNet to full-disk Halpha images from other solar observatories and additional high-resolution Halpha images collected by BBSO/GST, demonstrating the tool's usability in diverse datasets.

Haodi Jiang, Jiasheng Wang, Chang Liu et al.

Deep learning has drawn a lot of interest in recent years due to its effectiveness in processing big and complex observational data gathered from diverse instruments. Here we propose a new deep learning method, called SolarUnet, to identify and track solar magnetic flux elements or features in observed vector magnetograms based on the Southwest Automatic Magnetic Identification Suite (SWAMIS). Our method consists of a data pre-processing component that prepares training data from the SWAMIS tool, a deep learning model implemented as a U-shaped convolutional neural network for fast and accurate image segmentation, and a post-processing component that prepares tracking results. SolarUnet is applied to data from the 1.6 meter Goode Solar Telescope at the Big Bear Solar Observatory. When compared to the widely used SWAMIS tool, SolarUnet is faster while agreeing mostly with SWAMIS on feature size and flux distributions, and complementing SWAMIS in tracking long-lifetime features. Thus, the proposed physics-guided deep learning-based tool can be considered as an alternative method for solar magnetic tracking.

Hao Liu, Yan Xu, Jiasheng Wang et al.

We propose a new machine learning approach to Stokes inversion based on a convolutional neural network (CNN) and the Milne-Eddington (ME) method. The Stokes measurements used in this study were taken by the Near InfraRed Imaging Spectropolarimeter (NIRIS) on the 1.6 m Goode Solar Telescope (GST) at the Big Bear Solar Observatory. By learning the latent patterns in the training data prepared by the physics-based ME tool, the proposed CNN method is able to infer vector magnetic fields from the Stokes profiles of GST/NIRIS. Experimental results show that our CNN method produces smoother and cleaner magnetic maps than the widely used ME method. Furthermore, the CNN method is 4~6 times faster than the ME method, and is able to produce vector magnetic fields in near real-time, which is essential to space weather forecasting. Specifically, it takes ~50 seconds for the CNN method to process an image of 720 x 720 pixels comprising Stokes profiles of GST/NIRIS. Finally, the CNN-inferred results are highly correlated to the ME-calculated results and are closer to the ME's results with the Pearson product-moment correlation coefficient (PPMCC) being closer to 1 on average than those from other machine learning algorithms such as multiple support vector regression and multilayer perceptrons (MLP). In particular, the CNN method outperforms the current best machine learning method (MLP) by 2.6% on average in PPMCC according to our experimental study. Thus, the proposed physics-assisted deep learning-based CNN tool can be considered as an alternative, efficient method for Stokes inversion for high resolution polarimetric observations obtained by GST/NIRIS.