6 papers
GuideWalk: Learning Unified Autonomous Navigation and Locomotion for Humanoid Robots across Versatile Terrains
Haoxuan Han, Chen Chen, Linao Gong +6
Humanoid robots have achieved strong locomotion capabilities, but reliable navigation on versatile terrains remains challenging because obstacle avoidance must be coordinated with…
Next Forcing: Causal World Modeling with Multi-Chunk Prediction
Gangwei Xu, Qihang Zhang, Jiaming Zhou +4
Autoregressive video generation has emerged as a powerful paradigm for World Action Models (WAMs). However, existing approaches suffer from slow training convergence and limited co…
HDSL: A Hierarchical Domain-Specific Language for Structured 3D Indoor Scene Generation and Localized Editing with LLM Agents
Letian Li, Chao Shen, Shuzhao Xie +6
Text-driven indoor scene generation and editing require an intermediate representation that language models can both produce and revise. Existing LLM-based systems often rely on sc…
cMoLLM at Scale: Horizontal Scaling Laws for Mixture-of-LLMs
Xin Yang, Yemin Wang, Mingda Liu +4
Scaling large language models (LLMs) has driven their success, yet dense Transformers couple capacity and computation: every parameter is activated for every token, making training…
PCSTracker: Long-Term Scene Flow Estimation for Point Cloud Sequences
Min Lin, Gangwei Xu, Xianqi Wang +2
Point cloud scene flow estimation is fundamental to long-term and fine-grained 3D motion analysis. However, existing methods are typically limited to pairwise settings and struggle…
FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation
Min Lin, Gangwei Xu, Yun Wang +2
Scene flow methods based on deep learning have achieved impressive performance. However, current top-performing methods still struggle with ill-posed regions, such as extensive fla…