Journaling is a well-established practice for reflecting on life events and constructing meaning; yet, finding concrete meaning from them remains challenging. Recent advances in generative AI demonstrate the potential to generate materials that support reflection, suggesting opportunities to assist meaning-making in journaling. However, prior approaches often center on ambiguous outputs and reflections of a single experience, leaving unexplored how concrete interpretations from AI can help self-reflection in journaling. In this study, we designed Augmentiary, an LLM-based journaling system that suggests candidate interpretations of experiences with concrete meaning while preserving users’ agency and voice, based on insights from a formative study with eight journal writers. We then conducted a four-week deployment study with 25 participants. Our findings show that AI’s interpretive feedback helped connect fragmented experiences and supported self-understanding through comparison with their own thoughts. Moreover, tensions between user agency and constructive reflection were revealed. We conclude by discussing design implications for AI-supported systems for fostering meaning-making without replacing users’ thinking.

Reconstructing 3Ds of hand-object interaction (HOI) is a fundamental problem that can find numerous applications. Despite recent advances, there is no comprehensive pipeline yet for bimanual class-agnostic interaction reconstruction from a monocular RGB video, where two hands and an unknown object are interacting with each other. Previous works tackled the limited hand-object interaction case, where object templates are pre-known or only one hand is involved in the interaction. The bimanual interaction reconstruction exhibits severe occlusions introduced by complex interactions between two hands and an object. To solve this, we first introduce BIGS (Bimanual Interaction 3D Gaussian Splatting), a method that reconstructs 3D Gaussians of hands and an unknown object from a monocular video. To robustly obtain object Gaussians avoiding severe occlusions, we leverage prior knowledge of pre-trained diffusion model with score distillation sampling (SDS) loss, to reconstruct unseen object parts. For hand Gaussians, we exploit the 3D priors of hand model (i.e., MANO) and share a single Gaussian for two hands to effectively accumulate hand 3D information, given limited views. To further consider the 3D alignment between hands and objects, we include the interacting-subjects optimization step during Gaussian optimization. Our method achieves the state-of-the-art accuracy on two challenging datasets, in terms of 3D hand pose estimation (MPJPE), 3D object reconstruction (CDh, CDo, F10), and rendering quality (PSNR, SSIM, LPIPS), respectively.