6 accepted papers
Existing 3D Visual Question Answering (3D-VQA) methods rely on generative paradigms, producing ambiguous descriptions that hinder deterministic decision-making. We introduce 3D Scene Assertion Verification, a task requiring models to verify natural language assertions in 3D scenes with strict binary…
Lifting 2D open-vocabulary understanding into 3D Gaussian Splatting (3DGS) scenes is a critical challenge. Mainstream methods, built on an embedding paradigm, suffer from three key flaws: (i) geometry-semantic inconsistency, where points, rather than objects, serve as the semantic basis, limiting se
Rich-format documents are essential for everyday operations yet costly to author, motivating the need for automated generation to enhance productivity. To this end, we present FormAct, an agentic system that generates professional rich-format documents from scratch. FormAct operates on an HTML sourc…
Graph-enhanced large language models (LLMs) leverage LLMs’ remarkable ability to model language and use graph structures to capture topological relationships. Existing graph-enhanced LLMs typically retrieve similar subgraphs to augment LLMs, where the subgraphs carry the entities related to our targ…
Modular robotics offers a promising approach for developing versatile and adaptive robotic systems capable of autonomous reconfiguration. This paper presents a novel modular robotic system in which each module is equipped with independent actuation, battery power, and control, enabling both individu
Symmetry manifests itself in legged locomotion in a variety of ways: A legged system can maintain consistent gaits from any spatial starting point, exhibiting the same leg movements on either side of the torso in phase, and some even demonstrate forward and backward movements so similar they seem to