4 papers
Towards Dexterous Embodied Manipulation via Deep Multi-Sensory Fusion and Sparse Expert Scaling
Yirui Sun, Guangyu Zhuge, Keliang Liu +5
Realizing dexterous embodied manipulation necessitates the deep integration of heterogeneous multimodal sensory inputs. However, current vision-centric paradigms often overlook the…
Gaussian Sequences with Multi-Scale Dynamics for 4D Reconstruction from Monocular Casual Videos
Can Li, Jie Gu, Jingmin Chen +2
Understanding dynamic scenes from casual videos is critical for scalable robot learning, yet four-dimensional (4D) reconstruction under strictly monocular settings remains highly i…
Egocentric Instruction-oriented Affordance Prediction via Large Multimodal Model
Bokai Ji, Jie Gu, Xiaokang Ma +3
Affordance is crucial for intelligent robots in the context of object manipulation. In this paper, we argue that affordance should be task-/instruction-dependent, which is overlook…
Task-Related Token Compression in Multimodal Large Language Models from an Explainability Perspective
Lei Lei, Jie Gu, Xiaokang Ma +3
Existing Multimodal Large Language Models (MLLMs) process a large number of visual tokens, leading to significant computational costs and inefficiency. Instruction-related visual t…