6 papers
GeoTLM: Geometry-aware Tactile-Language Models for Contact Motion Orientation Reasoning of Dynamic Objects
Qiutian Li, Zinan Liu, Lin Wang
Modern tactile-language models (TLMs) have shown potential for robot learning tasks, such as material and texture recognition. However, for contact-rich scenarios, these TLMs strug…
VL2Spike: Spike-driven Distillation from VLMs for Low-Power Visual Perception in Embodied AI
Zinan Liu, Eric Zheng, Soumyaratna Debnath +3
Spiking neural networks (SNNs) are brain-inspired, event-driven models that compute with sparse spikes, which enables highly efficient visual perception in resource-constrained emb…
Denoise and Align: Diffusion-Driven Foreground Knowledge Prompting for Open-Vocabulary Temporal Action Detection
Sa Zhu, Wanqian Zhang, Lin Wang +3
Open-Vocabulary Temporal Action Detection (OV-TAD) aims to localize and classify action segments of unseen categories in untrimmed videos, where effective alignment between action…
Watching Movies Like a Human: Egocentric Emotion Understanding for Embodied Companions
Ze Dong, Hao Shi, Zejia Gao +3
Embodied robotic agents often perceive movies through an egocentric screen-view interface rather than native cinematic footage, introducing domain shifts such as viewpoint distorti…
OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Camera
Hao Shi, Ze Wang, Shangwei Guo +6
Robust 3D semantic occupancy is crucial for legged/humanoid robots, yet most semantic scene completion (SSC) systems target wheeled platforms with forward-facing sensors. We presen…
Event-guided 3D Gaussian Splatting for Dynamic Human and Scene Reconstruction
Xiaoting Yin, Hao Shi, Kailun Yang +4
Reconstructing dynamic humans together with static scenes from monocular videos remains difficult, especially under fast motion, where RGB frames suffer from motion blur. Event cam…