Related papers: LacaDM: A Latent Causal Diffusion Model for Multio…

In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile. Our analysis reveals that the fundamental limitation lies in an inductive gap, models…

Diffusion-based world models have demonstrated strong capabilities in synthesizing realistic long-horizon trajectories for offline reinforcement learning (RL). However, many existing methods do not directly generate actions alongside states…

Multimodal learning has rapidly advanced visual understanding, largely via multimodal large language models (MLLMs) that use powerful LLMs as cognitive cores. In visual generation, however, these powerful core models are typically reduced…

In this work, we provide a systematic survey of Discrete Diffusion Language Models (dLLMs) and Discrete Diffusion Multimodal Language Models (dMLLMs). Unlike autoregressive (AR) models, dLLMs and dMLLMs adopt a multi-token, parallel…

The generalization ability of most meta-reinforcement learning (meta-RL) methods is largely limited to test tasks that are sampled from the same distribution used to sample training tasks. To overcome the limitation, we propose Latent…

Masked Diffusion Models (MDMs) provide an efficient non-causal alternative to autoregressive generation but often struggle with token dependencies and semantic incoherence due to their reliance on discrete marginal distributions. We address…

Deep Reinforcement Learning (DRL) has demonstrated strong performance in robotic control but remains susceptible to out-of-distribution (OOD) states, often resulting in unreliable actions and task failure. While previous methods have…

Object-centric learning aims to represent visual data with a set of object entities (a.k.a. slots), providing structured representations that enable systematic generalization. Leveraging advanced architectures like Transformers, recent…

Multi-agent reinforcement learning (MARL) methods often suffer from high sample complexity, limiting their use in real-world problems where data is sparse or expensive to collect. Although latent-variable world models have been employed to…

We develop a novel multi-objective reinforcement learning (MORL) framework to jointly optimize wireless network selection and autonomous driving policies in a multi-band vehicular network operating on conventional sub-6GHz spectrum and…

Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics. However, learning a global model that can generalize across different dynamics is a…

Multi-agent reinforcement learning for incomplete information environments has attracted extensive attention from researchers. However, due to the slow sample collection and poor sample exploration, there are still some problems in…

Decentralized Multi-Agent Reinforcement Learning (Dec-MARL) has emerged as a pivotal approach for addressing complex tasks in dynamic environments. Existing Multi-Agent Reinforcement Learning (MARL) methodologies typically assume a shared…

The conditional diffusion model has been demonstrated as an efficient tool for learning robot policies, owing to its advancement to accurately model the conditional distribution of policies. The intricate nature of real-world scenarios,…

Due to network delays and scalability limitations, clustered ad hoc networks widely adopt Reinforcement Learning (RL) for on-demand resource allocation. Albeit its demonstrated agility, traditional Model-Free RL (MFRL) solutions struggle to…

Prompt learning has garnered attention for its efficiency over traditional model training and fine-tuning. However, existing methods, constrained by inadequate theoretical foundations, encounter difficulties in achieving causally invariant…

Offline reinforcement learning (RL) holds promise as a means to learn high-reward policies from a static dataset, without the need for further environment interactions. However, a key challenge in offline RL lies in effectively stitching…

Latent variable models provide a powerful framework for incorporating and inferring unobserved factors in observational data. In causal inference, they help account for hidden factors influencing treatment or outcome, thereby addressing…

Data allocation plays a critical role in federated large language model (LLM) and small language models (SLMs) reasoning collaboration. Nevertheless, existing data allocation methods fail to address an under-explored challenge in…

Many sequential decision-making tasks involve optimizing multiple conflicting objectives, requiring policies that adapt to different user preferences. In multi-objective reinforcement learning (MORL), one widely studied approach} addresses…