8 accepted papers
Speech-language models (SLMs) offer a promising path toward unifying speech and text understanding and generation. However, challenges remain in achieving effective cross-modal alignment and high-quality speech generation. In this work, we systematically investigate the role of speech tokenizer desi
In the field of mixed-motive games, extensive multi-agent learning studies have explored the balance between egoism (individual interest), utilitarianism (collective interest), and egalitarianism (fairness). Traditional approaches often rely on manually designed reward functions, social norms, and a…
LoRA has become one of the most widely used parameter-efficient fine-tuning methods due to its simplicity and effectiveness. However, numerous studies have shown that LoRA often introduces substantial parameter redundancy, which not only increases the number of trainable parameters but also hinders
In Model-Based Reinforcement Learning (MBRL), incorporating causal structures into dynamics models provides agents with a structured understanding of the environments, enabling efficient decision. Empowerment as an intrinsic motivation enhances the ability of agents to actively control their enviro…
Self-learning and social learning stand as two pivotal constituents in multi-agent exploration. Inspired by the fact that animals and humans explore unfamiliar environments to learn survival skills by training themselves using unlabeled data and replicating others’ successful experiences, we propose…
Most real-world multi-agent tasks exhibit the characteristic of sparse interaction, wherein agents interact with each other in a limited number of crucial states while largely acting independently. Effectively modeling the sparse interaction and leveraging the learned interaction structure to instru…
In cooperative multi-agent reinforcement learning, decentralized agents hold the promise of overcoming the combinatorial explosion of joint action space and enabling greater scalability. However, they are susceptible to a game-theoretic pathology called relative overgeneralization that shadows the o…
In the few-shot learning scenario, the data-distribution discrepancy between training data and test data in a task usually exists due to the limited data. However, most existing meta-learning approaches seldom consider this intra-task discrepancy in the meta-training phase which might deteriorate th…