相关论文: Unified token representations for sequential decis…

The Decision Transformer (DT) has established a powerful sequence modeling approach to offline reinforcement learning. It conditions its action predictions on Return-to-Go (RTG), using it both to distinguish trajectory quality during…

Decision Transformer (DT) formulates offline reinforcement learning as autoregressive sequence modeling, achieving promising results by predicting actions from a sequence of Return-to-Go (RTG), state, and action tokens. However, RTG is a…

We present Token-UNet, adopting the TokenLearner and TokenFuser modules to encase Transformers into UNets. While Transformers have enabled global interactions among input elements in medical imaging, current computational challenges hinder…

Recurrent neural networks (RNNs) sequentially process data by updating their state with each new data point, and have long been the de facto choice for sequence modeling tasks. However, their inherently sequential computation makes them…

Token uniformity is commonly observed in transformer-based models, in which different tokens share a large proportion of similar information after going through stacked multiple self-attention layers in a transformer. In this paper, we…

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,…

Cross-domain shifts present a significant challenge for decision transformer (DT) policies. Existing cross-domain policy adaptation methods typically rely on a single simple filtering criterion to select source trajectory fragments and…

In the realm of online advertising, advertisers partake in ad auctions to obtain advertising slots, frequently taking advantage of auto-bidding tools provided by demand-side platforms. To improve the automation of these bidding systems, we…

In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel attention computations…

Deep learning has achieved remarkable success in modeling sequential data, including event sequences, temporal point processes, and irregular time series. Recently, transformers have largely replaced recurrent networks in these tasks.…

We propose Token Turing Machines (TTM), a sequential, autoregressive Transformer model with memory for real-world sequential visual understanding. Our model is inspired by the seminal Neural Turing Machine, and has an external memory…

Traditional approaches in offline reinforcement learning aim to learn the optimal policy that maximizes the cumulative reward, also known as return. It is increasingly important to adjust the performance of AI agents to meet human…

Transformers have revolutionized Computer Vision (CV) through self-attention mechanisms. However, their complexity makes latent token representations difficult to interpret. We introduce ULTra, a framework for interpreting Transformer…

This paper introduces a novel Token-and-Duration Transducer (TDT) architecture for sequence-to-sequence tasks. TDT extends conventional RNN-Transducer architectures by jointly predicting both a token and its duration, i.e. the number of…

Recently, the transform-based tensor representation has attracted increasing attention in multimedia data (e.g., images and videos) recovery problems, which consists of two indispensable components, i.e., transform and characterization.…

Quadrupeds have gained rapid advancement in their capability of traversing across complex terrains. The adoption of deep Reinforcement Learning (RL), transformers and various knowledge transfer techniques can greatly reduce the sim-to-real…

In recommendation systems, scaling up feature-interaction modules (e.g., Wukong, RankMixer) or user-behavior sequence modules (e.g., LONGER) has achieved notable success. However, these efforts typically proceed on separate tracks, which…

Offline reinforcement learning (RL) is a challenging task, whose objective is to learn policies from static trajectory data without interacting with the environment. Recently, offline RL has been viewed as a sequence modeling problem, where…

In-context learning is a new learning paradigm where a language model conditions on a few input-output pairs (demonstrations) and a test input, and directly outputs the prediction. It has been shown highly dependent on the provided…

We present Unified Latent Dynamics (ULD), a novel reinforcement learning algorithm that unifies the efficiency of model-free methods with the representational strengths of model-based approaches, without incurring planning overhead. By…