相关论文: StateLinFormer: Stateful Training Enhancing Long-t…

Long-term conversational agents need memory systems that capture relationships between events, not merely isolated facts, to support temporal reasoning and multi-hop question answering. Current approaches face a fundamental trade-off: flat…

Accurate vehicle trajectory prediction is crucial for ensuring safe and efficient autonomous driving. This work explores the integration of Transformer based model with Long Short-Term Memory (LSTM) based technique to enhance spatial and…

Transformer networks have lead to important progress in language modeling and machine translation. These models include two consecutive modules, a feed-forward layer and a self-attention layer. The latter allows the network to capture long…

Incorporating the dynamics knowledge into the model is critical for achieving accurate trajectory prediction while considering the spatial and temporal characteristics of the vessel. However, existing methods rarely consider the underlying…

This paper presents a novel approach for the Vision-and-Language Navigation (VLN) task in continuous 3D environments, which requires an autonomous agent to follow natural language instructions in unseen environments. Existing end-to-end…

Large language models (LLMs) can adapt to new tasks via in-context learning (ICL) without parameter updates, making them powerful learning engines for fast adaptation. While extensive research has examined ICL as a few-shot learner, whether…

Transformers suffer from a high computational cost that grows with sequence length for self-attention, making inference in long streams prohibited by memory consumption. Constant-memory alternatives such as RNNs and SSMs compress history…

Processing long temporal sequences is a key challenge in deep learning. In recent years, Transformers have become state-of-the-art for this task, but suffer from excessive memory requirements due to the need to explicitly store the…

Simultaneous localization and mapping (SLAM) with implicit neural representations has received extensive attention due to the expressive representation power and the innovative paradigm of continual learning. However, deploying such a…

Visual perception and navigation have emerged as major focus areas in the field of embodied artificial intelligence. We consider the task of image-goal navigation, where an agent is tasked to navigate to a goal specified by an image,…

Many autonomous systems face safety challenges, requiring robust closed-loop control to handle physical limitations and safety constraints. Real-world systems, like autonomous ships, encounter nonlinear dynamics and environmental…

Transformer-based language models (LMs) track contextual information through large, hard-coded input windows. We introduce MemoryPrompt, a leaner approach in which the LM is complemented by a small auxiliary recurrent network that passes…

In continual learning, solving the catastrophic forgetting problem may make the models fall into the stability-plasticity dilemma. Moreover, inter-task confusion will also occur due to the lack of knowledge exchanges between different…

We extend the recent latent recurrent modeling to sequential input streams. By interleaving fast, recurrent latent updates with self-organizational ability between slow observation updates, our method facilitates the learning of stable…

Transformers are unable to model long-term memories effectively, since the amount of computation they need to perform grows with the context length. While variations of efficient transformers have been proposed, they all have a finite…

State-space models (SSMs) offer a powerful framework for dynamical system analysis, wherein the temporal dynamics of the system are assumed to be captured through the evolution of the latent states, which govern the values of the…

Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we study these challenges in the context of sequential supervised learning with an emphasis on recurrent…

Modeling the parser state is key to good performance in transition-based parsing. Recurrent Neural Networks considerably improved the performance of transition-based systems by modelling the global state, e.g. stack-LSTM parsers, or local…

Pre-trained language models demonstrate general intelligence and common sense, but long inputs quickly become a bottleneck for memorizing information at inference time. We resurface a simple method, Memorizing Transformers (Wu et al.,…

Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context…