Related papers: Pretrained Vision-Language-Action Models are Surpr…
Robots trained via Reinforcement Learning (RL) or Imitation Learning (IL) often adapt slowly to new tasks, whereas recent Large Language Models (LLMs) and Vision-Language Models (VLMs) promise knowledge-rich planning from minimal data.…
Vision-Language-Action (VLA) models achieve preliminary generalization through pretraining on large scale robot teleoperation datasets. However, acquiring datasets that comprehensively cover diverse tasks and environments is extremely…
Continual learning is conventionally tackled through sequential fine-tuning, a process that, while enabling adaptation, inherently favors plasticity over the stability needed to retain prior knowledge. While existing approaches attempt to…
Vision-Language-Action (VLA) models have emerged as a popular paradigm for learning robot manipulation policies that can follow language instructions and generalize to novel scenarios. Recent works have begun to explore the incorporation of…
Achieving truly adaptive embodied intelligence requires agents that learn not just by imitating static demonstrations, but by continuously improving through environmental interaction, which is akin to how humans master skills through…
Recent advancements in Vision-Language-Action (VLA) models have leveraged pre-trained Vision-Language Models (VLMs) to improve the generalization capabilities. VLMs, typically pre-trained on vision-language understanding tasks, provide rich…
Vision-language-action (VLA) models show promising knowledge accumulation ability from pretraining, yet continual learning in VLA remains challenging, especially for efficient adaptation. Existing continual imitation learning (CIL) methods…
The growing success of Vision-Language-Action (VLA) models stems from the promise that pretrained Vision-Language Models (VLMs) can endow agents with transferable world knowledge and vision-language (VL) grounding, laying a foundation for…
Continual Learning (CL) considers the problem of training an agent sequentially on a set of tasks while seeking to retain performance on all previous tasks. A key challenge in CL is catastrophic forgetting, which arises when performance on…
Neural networks suffer from catastrophic forgetting and are unable to sequentially learn new tasks without guaranteed stationarity in data distribution. Continual learning could be achieved via replay -- by concurrently training externally…
Lifelong learning requires models that can continuously learn from sequential streams of data without suffering catastrophic forgetting due to shifts in data distributions. Deep learning models have thrived in the non-sequential learning…
Humans possess a unified cognitive ability to perceive, comprehend, and interact with the physical world. Why can't large language models replicate this holistic understanding? Through a systematic analysis of existing training paradigms in…
Continual learning aims to learn new tasks without forgetting previously learned ones. We hypothesize that representations learned to solve each task in a sequence have a shared structure while containing some task-specific properties. We…
With the burgeoning amount of data of image-text pairs and diversity of Vision-and-Language (V\&L) tasks, scholars have introduced an abundance of deep learning models in this research domain. Furthermore, in recent years, transfer learning…
Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for…
While Vision-Language-Action (VLA) models show strong promise for generalist robot control, it remains unclear whether -- and under what conditions -- the standard "scale data" recipe translates to robotics, where training data is…
Temporal context is essential for robotic manipulation because such tasks are inherently non-Markovian, yet mainstream VLA models typically overlook it and struggle with long-horizon, temporally dependent tasks. Cognitive science suggests…
Vision-Language-Action models have recently emerged as a powerful paradigm for general-purpose robot learning, enabling agents to map visual observations and natural-language instructions into executable robotic actions. Though popular,…
The pursuit of out-of-distribution generalization in Vision-Language-Action (VLA) models is often hindered by catastrophic forgetting of the Vision-Language Model (VLM) backbone during fine-tuning. While co-training with external reasoning…
Large language models (LLMs) often suffer from catastrophic forgetting in continual learning: after learning new tasks sequentially, they perform worse on earlier tasks. Existing methods mitigate catastrophic forgetting by data replay,…