3 citations · 15 across the 27 of their papers we have counts for
14 papers · 1 filter
CoA-VLA: Improving Vision-Language-Action Models via Visual-Textual Chain-of-Affordance
Jinming Li, Yichen Zhu, Zhibin Tang +8
Robot foundation models, particularly Vision-Language-Action (VLA) models, have garnered significant attention for their ability to enhance robot policy learning, greatly improving…
Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoning
Junjie Wen, Minjie Zhu, Yichen Zhu +8
In this paper, we present DiffusionVLA, a novel framework that seamlessly combines the autoregression model with the diffusion model for learning visuomotor policy. Central to our…
EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching
Xinwang Chen, Ning Liu, Yichen Zhu +2
Transformer-based Diffusion Probabilistic Models (DPMs) have shown more potential than CNN-based DPMs, yet their extensive computational requirements hinder widespread practical ap…
Discrete Policy: Learning Disentangled Action Space for Multi-Task Robotic Manipulation
Kun Wu, Yichen Zhu, Jinming Li +4
Learning visuomotor policy for multi-task robotic manipulation has been a long-standing challenge for the robotics community. The difficulty lies in the diversity of action space:…
Scaling Diffusion Policy in Transformer to 1 Billion Parameters for Robotic Manipulation
Minjie Zhu, Yichen Zhu, Jinming Li +8
Diffusion Policy is a powerful technique tool for learning end-to-end visuomotor robot control. It is expected that Diffusion Policy possesses scalability, a key attribute for deep…
TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation
Junjie Wen, Yichen Zhu, Jinming Li +9
Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes. However, current VLA…
MMRo: Are Multimodal LLMs Eligible as the Brain for In-Home Robotics?
Jinming Li, Yichen Zhu, Zhiyuan Xu +7
It is fundamentally challenging for robots to serve as useful assistants in human environments because this requires addressing a spectrum of sub-problems across robotics, includin…
Retrieval-Augmented Embodied Agents
Yichen Zhu, Zhicai Ou, Xiaofeng Mou +1
Embodied agents operating in complex and uncertain environments face considerable challenges. While some advanced agents handle complex manipulation tasks with proficiency, their s…
Mipha: A Comprehensive Overhaul of Multimodal Assistant with Small Language Models
Minjie Zhu, Yichen Zhu, Xin Liu +7
Multimodal Large Language Models (MLLMs) have showcased impressive skills in tasks related to visual understanding and reasoning. Yet, their widespread application faces obstacles…
LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model
Yichen Zhu, Minjie Zhu, Ning Liu +3
In this paper, we introduce LLaVA- (LLaVA-Phi), an efficient multi-modal assistant that harnesses the power of the recently advanced small language model, Phi-2, to facilitate m…
Language-Conditioned Robotic Manipulation with Fast and Slow Thinking
Minjie Zhu, Yichen Zhu, Jinming Li +8
The language-conditioned robotic manipulation aims to transfer natural language instructions into executable actions, from simple pick-and-place to tasks requiring intent recogniti…
Object-Centric Instruction Augmentation for Robotic Manipulation
Junjie Wen, Yichen Zhu, Minjie Zhu +8
Humans interpret scenes by recognizing both the identities and positions of objects in their observations. For a robot to perform tasks such as \enquote{pick and place}, understand…
EPSD: Early Pruning with Self-Distillation for Efficient Model Compression
Dong Chen, Ning Liu, Yichen Zhu +6
Neural network compression techniques, such as knowledge distillation (KD) and network pruning, have received increasing attention. Recent work `Prune, then Distill' reveals that a…
Visual Robotic Manipulation with Depth-Aware Pretraining
Wanying Wang, Jinming Li, Yichen Zhu +7
Recent work on visual representation learning has shown to be efficient for robotic manipulation tasks. However, most existing works pretrained the visual backbone solely on 2D ima…