相关论文: UniZero: Generalized and Efficient Planning with S…

Transformer based diffusion and vision-language models have achieved remarkable success; yet, efficiently removing undesirable or sensitive information without retraining remains a central challenge for model safety and compliance. We…

Test-time reasoning significantly enhances pre-trained AI agents' performance. However, it requires an explicit environment model, often unavailable or overly complex in real-world scenarios. While MuZero enables effective model learning…

Recently, world models have made significant progress in enhancing end-to-end driving systems through both future situation forecasting and improved scene understanding. However, existing driving world models are typically built upon dense…

Fine-tuning is powerful for adapting large language models to downstream tasks, but it often results in huge memory usages. A promising approach to mitigate this is using Zeroth-Order (ZO) optimization, which estimates gradients to replace…

World Models have vastly permeated the field of Reinforcement Learning. Their ability to model the transition dynamics of an environment have greatly improved sample efficiency in online RL. Among them, the most notorious example is…

World models significantly enhance hierarchical understanding, improving data integration and learning efficiency. To explore the potential of the world model in the remote sensing (RS) field, this paper proposes a label-efficient remote…

Large Language Models (LLMs) offer extensive knowledge across various domains, but they may inadvertently memorize sensitive, unauthorized, or malicious data, such as personal information in the medical and financial sectors. Machine…

Heterogeneity in sensors and actuators across environments poses a significant challenge to building large-scale pre-trained world models on top of this low-dimensional sensor information. In this work, we explore pre-training world models…

Combinatorial Optimization (CO) encompasses a wide range of problems that arise in many real-world scenarios. While significant progress has been made in developing learning-based methods for specialized CO problems, a unified model with a…

Achieving reliable and efficient planning in complex driving environments requires a model that can reason over the scene's geometry, appearance, and dynamics. We present UniDWM, a unified driving world model that advances autonomous…

Existed pre-training methods either focus on single-modal tasks or multi-modal tasks, and cannot effectively adapt to each other. They can only utilize single-modal data (i.e. text or image) or limited multi-modal data (i.e. image-text…

The enduring challenge in the field of artificial intelligence has been the control of systems to achieve desired behaviours. While for systems governed by straightforward dynamics equations, methods like Linear Quadratic Regulation (LQR)…

This paper introduces a novel approach to enhance the capabilities of Large Language Models (LLMs) in processing and understanding extensive text sequences, a critical aspect in applications requiring deep comprehension and synthesis of…

Offline Reinforcement Learning (RL) enables policy learning without active interactions, making it especially appealing for self-driving tasks. Recent successes of Transformers inspire casting offline RL as sequence modeling, which,…

Planning methods struggle with computational intractability in solving task-level problems in large-scale environments. This work explores leveraging the commonsense knowledge encoded in LLMs to empower planning techniques to deal with…

Model-based reinforcement learning (MBRL) offers an intuitive way to increase the sample efficiency of model-free RL methods by simultaneously training a world model that learns to predict the future. These models constitute the large…

We investigate the effectiveness of adaptive zeroth-order (ZO) optimization for memory-constrained fine-tuning of large language models (LLMs). Contrary to prior claims, we show that adaptive ZO methods such as ZO-Adam offer no convergence…

Scaling data and models has played a pivotal role in the remarkable progress of computer vision and language. Inspired by these domains, recent efforts in robotics have similarly focused on scaling both data and model size to develop more…

In an environment where a manipulator needs to execute multiple consecutive tasks, the act of object manoeuvre will change the underlying configuration space, affecting all subsequent tasks. Previously free configurations might now be…

The combination of deep learning and Monte Carlo Tree Search (MCTS) has shown to be effective in various domains, such as board and video games. AlphaGo represented a significant step forward in our ability to learn complex board games, and…