Related papers: Procedural Scene Programs for Open-Universe Scene …
World models are central to LLM agents that must evaluate actions over long horizons. Yet much existing work focuses on environments governed by physical dynamics or spatial structure, whereas many high-impact domains, including supply…
3D point cloud understanding has made great progress in recent years. However, one major bottleneck is the scarcity of annotated real datasets, especially compared to 2D object detection tasks, since a large amount of labor is involved in…
Accurate estimates of item difficulty are essential for valid assessment and effective adaptive learning. However, for newly created tasks, response data are typically unavailable. Pretesting and expert judgement can be costly and slow,…
3D scene generation plays a crucial role in gaming, artistic creation, virtual reality, and many other domains. However, current 3D scene design still relies heavily on extensive manual effort from creators, and existing automated methods…
The rapid evolution of Large Language Models (LLMs) has markedly expanded their application across diverse domains, transforming how complex problems are approached and solved. Initially conceived to predict subsequent words in texts, these…
Scaling LLM-based embodied agents from text-only environments to complex multimodal settings remains a major challenge. Recent work identifies a perception-reasoning-decision gap in standalone Vision-Language Models (VLMs), which often…
The scarcity of data depicting dangerous situations presents a major obstacle to training AI systems for safety-critical applications, such as construction safety, where ethical and logistical barriers hinder real-world data collection.…
Generating human motions from textual descriptions has gained growing research interest due to its wide range of applications. However, only a few works consider human-scene interactions together with text conditions, which is crucial for…
Procedural mistake detection (PMD) is a challenging problem of classifying whether a human user (observed through egocentric video) has successfully executed a task (specified by a procedural text). Despite significant recent efforts,…
Recent advancements in multi-modal large language models (MLLMs) have shown strong potential for 3D scene understanding. However, existing methods struggle with fine-grained object grounding and contextual reasoning, limiting their ability…
Graphical user interface (UI) software has undergone a fundamental transformation from traditional two-dimensional (2D) desktop/web/mobile interfaces to spatial three-dimensional (3D) environments. While existing work has made remarkable…
Graphics design is important for various applications, including movie production and game design. To create a high-quality scene, designers usually need to spend hours in software like Blender, in which they might need to interleave and…
Learning and improving large language models through human preference feedback has become a mainstream approach, but it has rarely been applied to the field of low-light image enhancement. Existing low-light enhancement evaluations…
Despite advances in text-to-3D generation methods, generation of multi-object arrangements remains challenging. Current methods exhibit failures in generating physically plausible arrangements that respect the provided text description. We…
Video generation has witnessed remarkable progress with the advent of deep generative models, particularly diffusion models. While existing methods excel in generating high-quality videos from text prompts or single images, personalized…
Data center (DC) infrastructure serves as the backbone to support the escalating demand for computing capacity. Traditional design methodologies that blend human expertise with specialized simulation tools scale poorly with the increasing…
We propose an end-to-end variational generative model for scene layout synthesis conditioned on scene graphs. Unlike unconditional scene layout generation, we use scene graphs as an abstract but general representation to guide the synthesis…
Large Language Models (LLMs) are increasingly applied to automate software engineering tasks, including the generation of UML class diagrams from natural language descriptions. While prior work demonstrates that LLMs can produce…
Recent advancements in text-to-image (T2I) generative models have shown remarkable capabilities in producing diverse and imaginative visuals based on text prompts. Despite the advancement, these diffusion models sometimes struggle to…
Existing multi-agent video generation systems use LLM agents to orchestrate neural video generators, producing visually impressive but semantically unreliable outputs with no ground truth annotations. We present an agentic system that…