5 papers
VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing
Haoyuan Shi, Xiancong Ren, Yingji Zhang +9
Understanding how Vision-Language-Action (VLA) models transform multimodal knowledge into embodied control remains an open challenge. We present VLA-Trace, a progressive diagnostic…
EPIC-Bench: A Perception-Centric Benchmark for Fine-Grained Embodied Visual Grounding in Vision-Language Models
Haozhe Shan, Xiancong Ren, Han Dong +9
While large vision-language models (VLMs) are increasingly adopted as the perceptual backbone for embodied agents, existing benchmarks often rely on question-answering or multiple-…
Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization
Yi Zhang, Che Liu, Xiancong Ren +17
Developing a universal and versatile embodied intelligence system presents two primary challenges: the critical embodied data bottleneck, where real-world data is scarce and expens…
Separating the what and how of compositional computation to enable reuse and continual learning
Haozhe Shan, Sun Minni, Lea Duncker
The ability to continually learn, retain and deploy skills to accomplish goals is a key feature of intelligent and efficient behavior. However, the neural mechanisms facilitating t…
Order parameters and phase transitions of continual learning in deep neural networks
Haozhe Shan, Qianyi Li, Haim Sompolinsky
Continual learning (CL) enables animals to learn new tasks without erasing prior knowledge. CL in artificial neural networks (NNs) is challenging due to catastrophic forgetting, wh…