相关论文: MaIL: Improving Imitation Learning with Mamba

State Space Models (SSMs) like Mamba2 are a promising alternative to Transformers, with faster theoretical training and inference times -- especially for long context lengths. Recent work on Matryoshka Representation Learning -- and its…

Real-world applications require the classification model to adapt to new classes without forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a model with limited memory size to meet this requirement. Typical…

In recent years, Transformers have become the de-facto architecture for sequence modeling on text and a variety of multi-dimensional data, such as images and video. However, the use of self-attention layers in a Transformer incurs…

Linear RNN architectures, like Mamba, can be competitive with Transformer models in language modeling while having advantageous deployment characteristics. Given the focus on training large-scale Transformer models, we consider the…

We tackle a common scenario in imitation learning (IL), where agents try to recover the optimal policy from expert demonstrations without further access to the expert or environment reward signals. Except the simple Behavior Cloning (BC)…

U-shaped architectures have long dominated the field of medical image segmentation, while Transformers are widely employed for modeling long-range dependencies. The former typically handles scale variations implicitly by aggregating…

Imitation learning has been a trend recently, yet training a generalist agent across multiple tasks still requires large-scale expert demonstrations, which are costly and labor-intensive to collect. To address the challenge of limited…

Sequential recommendation systems aim to predict users' next preferences based on their interaction histories, but existing approaches face critical limitations in efficiency and multi-scale pattern recognition. While Transformer-based…

Imitation learning (IL) enables robots to acquire skills quickly by transferring expert knowledge, which is widely adopted in reinforcement learning (RL) to initialize exploration. However, in long-horizon motion planning tasks, a…

Recent advancements in reinforcement learning (RL) for analog circuit optimization have demonstrated significant potential for improving sample efficiency and generalization across diverse circuit topologies and target specifications.…

Model-Agnostic Meta-Learning (MAML) and its variants have achieved success in meta-learning tasks on many datasets and settings. On the other hand, we have just started to understand and analyze how they are able to adapt fast to new tasks.…

Transformers are the current architecture of choice for NLP, but their attention layers do not scale well to long contexts. Recent works propose to replace attention with linear recurrent layers -- this is the case for state space models,…

In recent years, the application of multimodal large language models (MLLM) in various fields has achieved remarkable success. However, as the foundation model for many downstream tasks, current MLLMs are composed of the well-known…

Recently, the robotics community has amassed ever larger and more diverse datasets to train generalist robot policies. However, while these policies achieve strong mean performance across a variety of tasks, they often underperform on…

Continual Learning (CL) aims to equip AI models with the ability to learn a sequence of tasks over time, without forgetting previously learned knowledge. Recently, State Space Models (SSMs), particularly the Mamba model, have achieved…

State space models (SSMs) for language modelling promise an efficient and performant alternative to quadratic-attention Transformers, yet show variable performance on recalling basic information from the context. While performance on…

Multi-agent reinforcement learning (MARL) methods often suffer from high sample complexity, limiting their use in real-world problems where data is sparse or expensive to collect. Although latent-variable world models have been employed to…

State Space Models (SSMs) have become serious contenders in the field of sequential modeling, challenging the dominance of Transformers. At the same time, Mixture of Experts (MoE) has significantly improved Transformer-based Large Language…

This study explores replacing Transformers in Visual Language Models (VLMs) with Mamba, a recent structured state space model (SSM) that demonstrates promising performance in sequence modeling. We test models up to 3B parameters under…

Model Agnostic Meta-Learning (MAML) is one of the most representative of gradient-based meta-learning algorithms. MAML learns new tasks with a few data samples using inner updates from a meta-initialization point and learns the…