Related papers: Learning to Forget -- Hierarchical Episodic Memory…

Current generation of memory-augmented neural networks has limited scalability as they cannot efficiently process data that are too large to fit in the external memory storage. One example of this is lifelong learning scenario where the…

Although long-term memory systems have made substantial progress in recent years, they still exhibit clear limitations in adaptability, scalability, and self-evolution under continuous interaction settings. Inspired by cognitive theories,…

Inspired by the cognitive science theory of the explicit human memory systems, we have modeled an agent with short-term, episodic, and semantic memory systems, each of which is modeled with a knowledge graph. To evaluate this system and…

We present a novel deep neural network architecture for representing robot experiences in an episodic-like memory which facilitates encoding, recalling, and predicting action experiences. Our proposed unsupervised deep episodic memory model…

Current deep neural networks can achieve remarkable performance on a single task. However, when the deep neural network is continually trained on a sequence of tasks, it seems to gradually forget the previous learned knowledge. This…

The integration of large language models (LLMs) into conversational robots has made human-robot conversations more dynamic. Yet, LLM-powered conversational robots remain prone to errors, e.g., misunderstanding user intent, prematurely…

Transformer-based large language models (LLM) have been widely used in language processing applications. However, due to the memory constraints of the devices, most of them restrict the context window. Even though recurrent models in…

Spatial memory, or the ability to remember and recall specific locations and objects, is central to autonomous agents' ability to carry out tasks in real environments. However, most existing artificial memory modules are not very adept at…

Reinforcement learning agents often forget details of the past, especially after delays or distractor tasks. Agents with common memory architectures struggle to recall and integrate across multiple timesteps of a past event, or even to…

Large language model (LLM)-based agents have shown strong potential in multi-task scenarios, owing to their ability to transfer knowledge across diverse tasks. However, existing approaches often treat prior experiences and knowledge as…

Spatial reasoning is a critical capability for intelligent robots, yet current vision-language models (VLMs) still fall short of human-level performance in video-based spatial reasoning. This gap mainly stems from two challenges: a…

The hallmark of human intelligence is the self-evolving ability to master new skills by learning from past experiences. However, current AI agents struggle to emulate this self-evolution: fine-tuning is computationally expensive and prone…

Lifelong event detection aims to incrementally update a model with new event types and data while retaining the capability on previously learned old types. One critical challenge is that the model would catastrophically forget old types…

Automatic speech recognition (ASR) technologies today are primarily optimized for given datasets; thus, any changes in the application environment (e.g., acoustic conditions or topic domains) may inevitably degrade the performance. We can…

Reinforcement learning agents deployed in the real world often have to cope with partially observable environments. Therefore, most agents employ memory mechanisms to approximate the state of the environment. Recently, there have been…

Video Large Language Models (Video-LLMs) have shown strong video understanding, yet their application to long-form videos remains constrained by limited context windows. A common workaround is to compress long videos into a handful of…

Despite rapid progress in large-scale language and vision models, AI agents still suffer from a fundamental limitation: they cannot remember. Without reliable memory, agents catastrophically forget past experiences, struggle with…

State of the art deep reinforcement learning algorithms are sample inefficient due to the large number of episodes they require to achieve asymptotic performance. Episodic Reinforcement Learning (ERL) algorithms, inspired by the mammalian…

A fundamental objective in intelligent robotics is to move towards lifelong learning robot that can learn and adapt to unseen scenarios over time. However, continually learning new tasks would introduce catastrophic forgetting problems due…

As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is intuitively appealing, existing approaches remain limited: full trajectories are often too…