Related papers: CKT-WAM: Parameter-Efficient Context Knowledge Tra…

Traditional reinforcement learning (RL)-based learning approaches for wireless networks rely on expensive trial-and-error mechanisms and real-time feedback based on extensive environment interactions, which leads to low data efficiency and…

Knowledge Distillation (KD) based methods adopt the one-way Knowledge Transfer (KT) scheme in which training a lower-capacity student network is guided by a pre-trained high-capacity teacher network. Recently, Deep Mutual Learning (DML)…

End-to-end autonomous driving seeks to solve the perception, decision, and control problems in an integrated way, which can be easier to generalize at scale and be more adapting to new scenarios. However, high costs and risks make it very…

Navigation is a fundamental skill of agents with visual-motor capabilities. We introduce a Navigation World Model (NWM), a controllable video generation model that predicts future visual observations based on past observations and…

In the framework of learned image compression, the context model plays a pivotal role in capturing the dependencies among latent representations. To reduce the decoding time resulting from the serial autoregressive context model, the…

Most knowledge distillation (KD) methodologies predominantly focus on teacher-student pairs with similar architectures, such as both being convolutional neural networks (CNNs). However, the potential and flexibility of KD can be greatly…

We propose Meta-World Conditional Neural Processes (MW-CNP), a conditional world model generator that leverages sample efficiency and scalability of Conditional Neural Processes to enable an agent to sample from its own "hallucination". We…

Standard transformer-based language models, while powerful for general text, often struggle with the fine-grained syntax and entity relationships in complex technical, engineering documents. To address this, we propose the Contextual Graph…

We propose an efficient knowledge transfer approach for model-based reinforcement learning, addressing the challenge of deploying large world models in resource-constrained environments. Our method distills a high-capacity multi-task agent…

A World Model is a compressed spatial and temporal representation of a real world environment that allows one to train an agent or execute planning methods. However, world models are typically trained on observations from the real world…

We propose a simple modification to existing neural machine translation (NMT) models that enables using a single universal model to translate between multiple languages while allowing for language specific parameterization, and that can…

Modern artificial intelligence systems depend heavily on large datasets for both training and transferring knowledge between models. Knowledge distillation, transfer learning, and dataset distillation have made such transfers more…

Imitation learning has emerged as a promising approach towards building generalist robots. However, scaling imitation learning for large robot foundation models remains challenging due to its reliance on high-quality expert demonstrations.…

Access to external knowledge is essential for many natural language processing tasks, such as question answering and dialogue. Existing methods often rely on a parametric model that stores knowledge in its parameters, or use a…

Humanoid robot loco-manipulation remains constrained by the semantic-physical gap. Current methods face three limitations: Low sample efficiency in reinforcement learning, poor generalization in imitation learning, and physical…

Camera-controllable video generation aims to synthesize videos with flexible and physically plausible camera movements. However, existing methods either provide imprecise camera control from text prompts or rely on labor-intensive manual…

Large Language Models (LLMs) can serve as world models to enhance agent decision-making in digital environments by simulating future states and predicting action outcomes, potentially eliminating costly trial-and-error exploration. However,…

Anticipating future actions is a highly challenging task due to the diversity and scale of potential future actions; yet, information from different modalities help narrow down plausible action choices. Each modality can provide diverse and…

Language Models (LMs) encode substantial knowledge in their parameters, yet it remains unclear how to transfer such knowledge in a fine-grained manner, namely parametric knowledge transfer (PKT). A central challenge is to make cross-scale…

Recent advances in transformer-based Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their quadratic computational complexity concerning sequence length remains a significant bottleneck…