Text-based generation and editing of 3D scenes hold significant potential for streamlining content creation through intuitive user interactions. While recent advances leverage 3D Gaussian Splatting (3DGS) for high-fidelity and real-time rendering, existing methods are often specialized and task-focused, lacking a unified framework for both generation and editing. In this paper, we introduce SplatFlow, a comprehensive framework that addresses this gap by enabling direct 3DGS generation and editing. SplatFlow comprises two main components: a multi-view rectified flow (RF) model and a Gaussian Splatting Decoder (GSDecoder). The multi-view RF model operates in latent space, generating multi-view images, depths, and camera poses simultaneously, conditioned on text prompts—thus addressing challenges like diverse scene scales and complex camera trajectories in real-world settings. Then, the GSDecoder efficiently translates these latent outputs into 3DGS representations through a feed-forward 3DGS method. Leveraging training-free inversion and inpainting techniques, SplatFlow enables seamless 3DGS editing and supports a broad range of 3D tasks—including object editing, novel view synthesis, and camera pose estimation—within a unified framework without requiring additional complex pipelines. We validate SplatFlow’s capabilities on the MVImgNet and DL3DV-7K datasets, demonstrating its versatility and effectiveness in various 3D generation, editing, and inpainting-based tasks. Our project page is available at https://gohyojun15.github.io/SplatFlow/.

Diffusion-based generative models have emerged as powerful tools in the realm of generative modeling. Despite extensive research on denoising across various timesteps and noise levels, a conflict persists regarding the relative difficulties of the denoising tasks. While various studies argue that lower timesteps present more challenging tasks, others contend that higher timesteps are more difficult. To address this conflict, our study undertakes a comprehensive examination of task difficulties, focusing on convergence behavior and changes in relative entropy between consecutive probability distributions across timesteps. Our observational study reveals that denoising at earlier timesteps poses challenges characterized by slower convergence and higher relative entropy, indicating increased task difficulty at these lower timesteps. Building on these observations, we introduce an easy-to-hard learning scheme, drawing from curriculum learning, to enhance the training process of diffusion models. By organizing timesteps or noise levels into clusters and training models with ascending orders of difficulty, we facilitate an order-aware training regime, progressing from easier to harder denoising tasks, thereby deviating from the conventional approach of training diffusion models simultaneously across all timesteps. Our approach leads to improved performance and faster convergence by leveraging benefits of curriculum learning, while maintaining orthogonality with existing improvements in diffusion training techniques. We validate these advantages through comprehensive experiments in image generation tasks, including unconditional, class-conditional, and text-to-image generation.

Large Language Models (LLMs) have a great potential to serve as readily available and costefficient Conversational Intelligent Tutoring Systems (CITS) for teaching L2 learners of English.Existing CITS, however, are designed to teach only simple concepts or lack the pedagogical depth necessary to address diverse learning strategies.To develop a more pedagogically informed CITS capable of teaching complex concepts, we construct a BIlingual PEDagogicallyinformed Tutoring Dataset (BIPED) of oneon-one, human-to-human English tutoring interactions.Through post-hoc analysis of the tutoring interactions, we come up with a lexicon of dialogue acts (34 tutor acts and 9 student acts), which we use to further annotate the collected dataset.Based on a two-step framework of first predicting the appropriate tutor act then generating the corresponding response, we implemented two CITS models using GPT-4 and SOLAR-KO, respectively.We experimentally demonstrate that the implemented models not only replicate the style of human teachers but also employ diverse and contextually appropriate pedagogical strategies.* We confine the utilization of data to a subset that has been fully annotated, despite a larger volume of collected data.

Online videos are a promising medium for older adults to learn. Yet, few studies have investigated what, how, and why they learn through online videos. In this study, we investigated older adults’ motivation, watching patterns, and difficulties in using online videos for learning by (1) running interviews with 13 older adults and (2) analyzing large-scale video event logs (N=41.8M) from a Korean Massive Online Open Course (MOOC) platform. Our results show that older adults (1) are motivated to learn practical topics, leading to less consumption of STEM domains than non-older adults, (2) watch videos with less interaction and watch a larger portion of a single video compared to non-older adults, and (3) face various difficulties (e.g., inconvenience arisen due to their unfamiliarity with technologies) that limit their learning through online videos. Based on the findings, we propose design guidelines for online videos and platforms targeted to support older adults’ learning.

Computerized Adaptive Testing (CAT) is a widely used, efficient test mode that adapts to the examinee's proficiency level in the test domain. CAT requires pre-trained item profiles, for CAT iteratively assesses the student real-time based on the registered items' profiles, and selects the next item to administer using candidate items' profiles. However, obtaining such item profiles is a costly process that involves gathering a large, dense item-response data, then training a diagnostic model on the collected data. In this paper, we explore the possibility of leveraging response data collected in the CAT service. We first show that this poses a unique challenge due to the inherent selection bias introduced by CAT, i.e., more proficient students will receive harder questions. Indeed, when naïvely training the diagnostic model using CAT response data, we observe that item profiles deviate significantly from the ground-truth. To tackle the selection bias issue, we propose the user-wise aggregate influence function method. Our intuition is to filter out users whose response data is heavily biased in an aggregate manner, as judged by how much perturbation the added data will introduce during parameter estimation. This way, we may enhance the performance of CAT while introducing minimal bias to the item profiles. We provide extensive experiments to demonstrate the superiority of our proposed method based on the three public datasets and one dataset that contains real-world CAT response data.

Finding an optimal learning trajectory is an important question in educational systems. Existing Artificial Intelligence in Education (AiEd) technologies mostly used indirect methods to make the learning process efficient such as recommending contents based on difficulty adjustment, weakness analysis, learning theory, psychometric analysis, or domain specific rules.