相关论文: MaIL: Improving Imitation Learning with Mamba

This paper introduces Bio-Inspired Mamba (BIM), a novel online learning framework for selective state space models that integrates biological learning principles with the Mamba architecture. BIM combines Real-Time Recurrent Learning (RTRL)…

Physics-informed machine learning (PIML) has emerged as a promising alternative to classical methods for predicting dynamical systems, offering faster and more generalizable solutions. However, existing models, including recurrent neural…

Offline Imitation Learning (IL) methods such as Behavior Cloning are effective at acquiring complex robotic manipulation skills. However, existing IL-trained policies are confined to executing the task at the same speed as shown in…

State of the art foundation models such as GPT-4 perform surprisingly well at in-context learning (ICL), a variant of meta-learning concerning the learned ability to solve tasks during a neural network forward pass, exploiting contextual…

Recent advancements in imitation learning have been largely fueled by the integration of sequence models, which provide a structured flow of information to effectively mimic task behaviours. Currently, Decision Transformer (DT) and…

Interactive Imitation Learning (IIL) is a branch of Imitation Learning (IL) where human feedback is provided intermittently during robot execution allowing an online improvement of the robot's behavior. In recent years, IIL has increasingly…

Adversarial Imitation Learning (AIL) is a broad family of imitation learning methods designed to mimic expert behaviors from demonstrations. While AIL has shown state-of-the-art performance on imitation learning with only small number of…

The Mamba model has gained significant attention for its computational advantages over Transformer-based models, while achieving comparable performance across a wide range of language tasks. Like Transformers, Mamba exhibits in-context…

Recent Mamba-based architectures for video understanding demonstrate promising computational efficiency and competitive performance, yet struggle with overfitting issues that hinder their scalability. To overcome this challenge, we…

Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement…

Sequence models like Transformers and RNNs often overallocate attention to irrelevant context, leading to noisy intermediate representations. This degrades LLM capabilities by promoting hallucinations, weakening long-range and retrieval…

Recently, pathological diagnosis has achieved superior performance by combining deep learning models with the multiple instance learning (MIL) framework using whole slide images (WSIs). However, the giga-pixeled nature of WSIs poses a great…

In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine…

Recent work has shown that state space models such as Mamba are significantly worse than Transformers on recall-based tasks due to the fact that their state size is constant with respect to their input sequence length. But in practice,…

Transformer structure has achieved great success in multiple applied machine learning communities, such as natural language processing (NLP), computer vision (CV) and information retrieval (IR). Transformer architecture's core mechanism\,…

Despite the remarkable quality of LLM-based text-to-speech systems, their reliance on autoregressive Transformers leads to quadratic computational complexity, which severely limits practical applications. Linear-time alternatives, notably…

In past years model-agnostic meta-learning (MAML) has been one of the most promising approaches in meta-learning. It can be applied to different kinds of problems, e.g., reinforcement learning, but also shows good results on few-shot…

Transformers dominate NLP and IR; but their inference inefficiencies and challenges in extrapolating to longer contexts have sparked interest in alternative model architectures. Among these, state space models (SSMs) like Mamba offer…

Long-short range time series forecasting is essential for predicting future trends and patterns over extended periods. While deep learning models such as Transformers have made significant strides in advancing time series forecasting, they…

We investigate in-context learning (ICL) through a meticulous experimental framework that systematically varies task complexity and model architecture. Extending beyond the linear regression baseline, we introduce Gaussian kernel regression…