Minh-Triet Tran

Xuan-Vu Le, Minh-Loi Nguyen, Khanh-Duy Le et al.

Story writing is a popular yet complex creative activity that requires organization of ideas and iterative exploration, particularly during early-stage ideation. While many AI-based writing assistants have been developed, existing approaches primarily focus on generating long-form coherent text and improving user controllability during text production, providing limited support for brainstorming, connecting ideas, and validating alternative narrative flows. We present GraphStory, an interactive writing support system that leverages a graph-based representation to provide a comprehensive view of narrative structure and facilitate ideation. The system enables users to organize and connect plot points, explore alternative branches, and validate evolving narratives through an integrated story generation workflow. It further provides a structured interface to support efficient iteration over multiple story paths. Results from a user study with professional and semi-professional writers show that GraphStory reduces the effort of organizing narrative structures and better supports creativity and exploration compared to normal AI-based writing workflows.

Duc-Manh Phan, Ngoc-Dai Tran, Duy-Khang Do et al.

Recent advances in generative AI have enabled natural language-driven image editing, yet existing systems often fail in complex scenes with multiple interacting objects because they rely heavily on users crafting precise text prompts. To address the absence of structured control, we propose SceneCraft, a novel interactive framework that bridges user intent and model execution by representing images as editable scene graphs. Instead of guessing text prompts through trial and error, users interact directly with a visual graph to perform complex spatial and relational operations. These graph modifications are automatically translated into precise, context-aware editing prompts, effectively eliminating linguistic ambiguity. To ensure robust and diverse results, structured prompts are dispatched to multiple state-of-the-art generative models. Evaluations across diverse editing scenarios show that SceneCraft provides a more intuitive control mechanism, significantly reducing the cognitive burden of manual prompt engineering while generating outputs that users consistently rate as higher in quality and fidelity.

Long-Bao Nguyen, Quang-Khai Tran, Tam V. Nguyen et al.

Multi-subject reference-based image generation requires jointly preserving multiple human identities, binding per-person objects and fashion items, and respecting a specified background scene, a regime where current diffusion models remain brittle. Existing benchmarks evaluate only one axis at a time and none jointly captures multi-identity composition with human-object interaction, background grounding, and spatial plausibility. We introduce CogCanvas, a benchmark of 1,952 curated reference images spanning 100 celebrity identities, 115 distinctive objects and fashion items, and 29 real-world background scenes including landmarks, from which we construct 1,361 compositional prompts covering 2-5 person group sizes. The curation pipeline combines DINOv2-based deduplication, two-stage aesthetic filtering, and automated derivation of structured interaction and position graphs that serve as ground-truth supervision. CogCanvas supports three tasks, reference-based multi-human-object generation (primary), text-to-image compositional generation, and reference retrieval, under a unified six-axis evaluation protocol. We introduce two metrics tailored to the multi-reference setting: BG-Sim, which scores background fidelity on SAM 3-masked regions via DINOv3 feature similarity, and Attr-VQA, which uses a multimodal LLM to verify per-subject attribute binding and inter-person interactions against the structured graphs. Benchmarking five SOTA methods reveals that every model degrades substantially as group size grows from 2 to 5, with near-complete failure on object/fashion binding beyond three subjects.