5 papers
ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes?
Han Li, Si Liu, Zehao Huang +6
Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse expert-level tasks, but they still struggle with fundamental abilities that humans naturall…
Generative Lane Topology Reasoning via Autoregressive Model with Geometry Prior
Jiahui Fu, Zehao Huang, Han Li +2
Lane topology reasoning aims to construct a lane graph from onboard sensor observations. Existing methods follow a detection and association paradigm that treats each lane instance…
Geometry-Guided 3D Visual Token Pruning for Video-Language Models
Han Li, Zehao Huang, Jiahui Fu +2
Multimodal large language models have demonstrated remarkable capabilities in 2D vision, motivating their extension to 3D scene understanding. Recent studies represent 3D scenes as…
NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planning
Jiahui Fu, Junyu Nan, Lingfeng Sun +5
Solving long-horizon tasks requires robots to integrate high-level semantic reasoning with low-level physical interaction. While vision-language models (VLMs) and video generation…
NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos
Hongyu Li, Lingfeng Sun, Yafei Hu +4
Enabling robots to execute novel manipulation tasks zero-shot is a central goal in robotics. Most existing methods assume in-distribution tasks or rely on fine-tuning with embodime…