29 citations · 29 across the 8 of their papers we have counts for
10 papers
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model
Kehan Li, Bohan Hou, Minghao Zhu +28
We present RynnBrain 1.1, a family of embodied foundation models spanning 2B, 9B, and 122B-A10B scales. Trained with a unified spatio-temporal and physically grounded framework, Ry…
MemPose: Category-level Object Pose Estimation with Memory
Xiao Lin, Minghao Zhu, Yun Peng +4
In the pursuit of robust and generalizable category-level object pose estimation, most existing methods adopt parametric formulations that learn effective representations from data…
TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition
Minghao Zhu, Xiao Lin, Mengxian Hu +5
Adapting CLIP for open-vocabulary video recognition necessitates a delicate balance between newly acquired video knowledge and the pretrained generalization. While existing studies…
GroundVTS: Visual Token Sampling in Multimodal Large Language Models for Video Temporal Grounding
Rong Fan, Kaiyan Xiao, Minghao Zhu +3
Video temporal grounding (VTG) is a critical task in video understanding and a key capability for extending video large language models (Vid-LLMs) to broader applications. However,…
RynnBrain: Open Embodied Foundation Models
Ronghao Dang, Jiayan Guo, Bohan Hou +23
Despite rapid progress in multimodal foundation models, embodied intelligence community still lacks a unified, physically grounded foundation model that integrates perception, reas…
CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillation
Xiao Lin, Yun Peng, Liuyi Wang +6
Category-level object pose estimation aims to recover the rotation, translation and size of unseen instances within predefined categories. In this task, deep neural network-based m…
MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer
Minghao Zhu, Zhengpu Wang, Mengxian Hu +5
Transferring visual-language knowledge from large-scale foundation models for video recognition has proved to be effective. To bridge the domain gap, additional parametric modules…
Efficient Text-driven Motion Generation via Latent Consistency Training
Mengxian Hu, Minghao Zhu, Xun Zhou +4
Text-driven human motion generation based on diffusion strategies establishes a reliable foundation for multimodal applications in human-computer interactions. However, existing ad…
CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge
Xiao Lin, Minghao Zhu, Ronghao Dang +5
Most of existing category-level object pose estimation methods devote to learning the object category information from point cloud modality. However, the scale of 3D datasets is li…
Fine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation Learning
Minghao Zhu, Xiao Lin, Ronghao Dang +2
As the most essential property in a video, motion information is critical to a robust and generalized video representation. To inject motion dynamics, recent works have adopted fra…