Related papers: Decision Mamba: Reinforcement Learning via Sequenc…
Transformers have increasingly outperformed gated RNNs in obtaining new state-of-the-art results on supervised tasks involving text sequences. Inspired by this trend, we study the question of how Transformer-based models can improve the…
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…
Multimodal large language models (MLLMs) have attracted widespread interest and have rich applications. However, the inherent attention mechanism in its Transformer structure requires quadratic complexity and results in expensive…
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…
In various domains, Sequential Recommender Systems (SRS) have become essential due to their superior capability to discern intricate user preferences. Typically, SRS utilize transformer-based architectures to forecast the subsequent item…
Selective State-Space Models (SSMs) such as Mamba have emerged as an alternative architecture to self-attention based transformers in sequence modeling tasks. Recent works have demonstrated the use of transformers in some filtering and…
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)…
Inductive biases influence the behavior and performance of sequential models. In this work, we study an underexplored inductive bias in sequential modeling: continuity in time. We ask a simple question: do models motivated by…
Motion forecasting is a crucial component of autonomous driving systems, enabling the generation of accurate and smooth future trajectories to ensure safe navigation to the destination. In previous methods, potential future trajectories are…
Transformer-based methods have demonstrated remarkable capabilities in 3D semantic segmentation through their powerful attention mechanisms, but the quadratic complexity limits their modeling of long-range dependencies in large-scale point…
Skeleton Action Recognition (SAR) involves identifying human actions using skeletal joint coordinates and their interconnections. While plain Transformers have been attempted for this task, they still fall short compared to the current…
Decision Transformer (DT) is an innovative algorithm leveraging recent advances of the transformer architecture in reinforcement learning (RL). However, a notable limitation of DT is its reliance on recalling trajectories from datasets,…
We propose Factorization Memory, an efficient recurrent neural network (RNN) architecture that achieves performance comparable to Transformer models on short-context language modeling tasks while also demonstrating superior generalization…
Decision Transformer-based decision-making agents have shown the ability to generalize across multiple tasks. However, their performance relies on massive data and computation. We argue that this inefficiency stems from the forgetting…
In applications such as e-commerce, online education, and streaming services, sequential recommendation systems play a critical role. Despite the excellent performance of self-attention-based sequential recommendation models in capturing…
Human engagement estimation in conversational scenarios is essential for applications such as adaptive tutoring, remote healthcare assessment, and socially aware human--computer interaction. Engagement is a dynamic, multimodal signal…
This paper works on streaming automatic speech recognition (ASR). Mamba, a recently proposed state space model, has demonstrated the ability to match or surpass Transformers in various tasks while benefiting from a linear complexity…
The Flexible Job Shop Problem (FJSP) is a well-studied combinatorial optimization problem with extensive applications for manufacturing and production scheduling. It involves assigning jobs to various machines to optimize criteria, such as…
As automation advances in manufacturing, the demand for precise and sophisticated defect detection technologies grows. Existing vision models for defect recognition methods are insufficient for handling the complexities and variations of…
Reinforcement learning presents an attractive paradigm to reason about several distinct aspects of sequential decision making, such as specifying complex goals, planning future observations and actions, and critiquing their utilities.…