相关论文: DREAMSTATE: Diffusing States and Parameters for Re…

Transformers have catalyzed advancements in computer vision and natural language processing (NLP) fields. However, substantial computational complexity poses limitations for their application in long-context tasks, such as high-resolution…

Transformers are highly parallel but are limited to computations in the TC$^0$ complexity class, excluding tasks such as entity tracking and code execution that provably require greater expressive power. Motivated by this limitation, we…

Transformers have revolutionized almost all natural language processing (NLP) tasks but suffer from memory and computational complexity that scales quadratically with sequence length. In contrast, recurrent neural networks (RNNs) exhibit…

Recurrent neural networks (RNNs) are a vital modeling technique that rely on internal states learned indirectly by optimization of a supervised, unsupervised, or reinforcement training loss. RNNs are used to model dynamic processes that are…

Neural-network quantum states (NQS) are powerful neural-network ans\"atzes that have emerged as promising tools for studying quantum many-body physics through the lens of the variational principle. These architectures are known to be…

The WuNeng architecture introduces a novel approach to enhancing the expressivity and power of large language models by integrating recurrent neural network (RNN)-based RWKV-7 with advanced attention mechanisms, prioritizing heightened…

Successful applications of reinforcement learning in real-world problems often require dealing with partially observable states. It is in general very challenging to construct and infer hidden states as they often depend on the agent's…

Models based on the Transformer architecture have seen widespread application across fields such as natural language processing, computer vision, and robotics, with large language models like ChatGPT revolutionizing machine understanding of…

The Receptance Weighted Key Value (RWKV) model offers a novel alternative to the Transformer architecture, merging the benefits of recurrent and attention-based systems. Unlike conventional Transformers, which depend heavily on…

Traditional Recurrent Neural Network (RNN) architectures, such as LSTM and GRU, have historically held prominence in time series tasks. However, they have recently seen a decline in their dominant position across various time series tasks.…

State-based sequence models like RWKV-7 offer a compelling alternative to Transformer architectures, achieving linear complexity while demonstrating greater expressive power in short-context scenarios and enabling state tracking beyond the…

Test-time scaling has emerged as a prominent research direction in machine learning, enabling models to enhance their expressive capabilities during inference.Transformers, renowned for striking a delicate balance between efficiency and…

We present Eagle (RWKV-5) and Finch (RWKV-6), sequence models improving upon the RWKV (RWKV-4) architecture. Our architectural design advancements include multi-headed matrix-valued states and a dynamic recurrence mechanism that improve…

Dynamic graph representation learning has emerged as a crucial research area, driven by the growing need for analyzing time-evolving graph data in real-world applications. While recent approaches leveraging recurrent neural networks (RNNs)…

This paper discusses models for dialogue state tracking using recurrent neural networks (RNN). We present experiments on the standard dialogue state tracking (DST) dataset, DSTC2. On the one hand, RNN models became the state of the art…

Recurrent Neural Networks (RNNs) continue to show outstanding performance in sequence modeling tasks. However, training RNNs on long sequences often face challenges like slow inference, vanishing gradients and difficulty in capturing long…

Neural-network quantum states (NQS) has emerged as a powerful application of quantum-inspired deep learning for variational Monte Carlo methods, offering a competitive alternative to existing techniques for identifying ground states of…

The extension of deep learning towards temporal data processing is gaining an increasing research interest. In this paper we investigate the properties of state dynamics developed in successive levels of deep recurrent neural networks…

This paper introduces an enhanced RWKV architecture with adaptive temporal gating mechanisms for improved long-context language modeling. We propose two principal innovations: (1) a position-aware convolutional shift operator that captures…

Recurrent neural networks (RNNs), temporal convolutions, and neural differential equations (NDEs) are popular families of deep learning models for time-series data, each with unique strengths and tradeoffs in modeling power and…