Related papers: Fast Spatial Memory with Elastic Test-Time Trainin…

Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific information, which can result in catastrophic forgetting and loss of…

Test-Time Training (TTT) models context dependencies by adapting part of the model's weights (referred to as fast weights) during inference. This fast weight, akin to recurrent states in RNNs, stores temporary memories of past tokens in the…

Associative memory using fast weights is a short-term memory mechanism that substantially improves the memory capacity and time scale of recurrent neural networks (RNNs). As recent studies introduced fast weights only to regular RNNs, it is…

The Long Short-Term Memory (LSTM) layer is an important advancement in the field of neural networks and machine learning, allowing for effective training and impressive inference performance. LSTM-based neural networks have been…

We propose tttLRM, a novel large 3D reconstruction model that leverages a Test-Time Training (TTT) layer to enable long-context, autoregressive 3D reconstruction with linear computational complexity, further scaling the model's capability.…

Long short-term memory (LSTM) is a robust recurrent neural network architecture for learning spatiotemporal sequential data. However, it requires significant computational power for learning and implementing from both software and hardware…

Adapting pretrained models typically involves a trade-off between the high training costs of backpropagation and the heavy inference overhead of memory-based or in-context learning. We propose FAAST, a forward-only associative adaptation…

Long short-term memory (LSTM) is one of the robust recurrent neural network architectures for learning sequential data. However, it requires considerable computational power to learn and implement both software and hardware aspects. This…

This paper investigates trajectory prediction for robotics, to improve the interaction of robots with moving targets, such as catching a bouncing ball. Unexpected, highly-non-linear trajectories cannot easily be predicted with…

Sparsity-aware training is an effective approach for transforming large language models (LLMs) into hardware-friendly sparse patterns, thereby reducing latency and memory consumption during inference. In this paper, we propose Continuous…

Incremental learning aims to adapt to new sets of categories over time with minimal computational overhead. Prior work often addresses this task by training efficient task-specific adaptors that modify frozen layer weights or features to…

Continual learning (CL) is essential for Large Language Models (LLMs) to adapt to evolving real-world demands, yet they are susceptible to catastrophic forgetting (CF). While traditional CF solutions rely on expensive data rehearsal, recent…

The field of lung nodule detection and cancer prediction has been rapidly developing with the support of large public data archives. Previous studies have largely focused on cross-sectional (single) CT data. Herein, we consider longitudinal…

Human action recognition in 3D skeleton sequences has attracted a lot of research attention. Recently, Long Short-Term Memory (LSTM) networks have shown promising performance in this task due to their strengths in modeling the dependencies…

Detecting 3D landmarks on cone-beam computed tomography (CBCT) is crucial to assessing and quantifying the anatomical abnormalities in 3D cephalometric analysis. However, the current methods are time-consuming and suffer from large biases…

Recurrent Neural Networks (RNNs) have become the state-of-the-art choice for extracting patterns from temporal sequences. However, current RNN models are ill-suited to process irregularly sampled data triggered by events generated in…

Humans can quickly associate stimuli to solve problems in novel contexts. Our novel neural network model learns state representations of facts that can be composed to perform such associative inference. To this end, we augment the LSTM…

Transformers have become the cornerstone of modern large-scale language models, but their reliance on softmax attention poses a computational bottleneck at both training and inference. Recurrent models offer high efficiency, but compressing…

Learning from spatio-temporal data has numerous applications such as human-behavior analysis, object tracking, video compression, and physics simulation.However, existing methods still perform poorly on challenging video tasks such as…

Humans excel at performing complex tasks by leveraging long-term memory across temporal and spatial experiences. In contrast, current Large Language Models (LLMs) struggle to effectively plan and act in dynamic, multi-room 3D environments.…