相关论文: Periodic Intra-Ensemble Knowledge Distillation for…

Knowledge distillation is a method of transferring the knowledge from a pretrained complex teacher model to a student model, so a smaller network can replace a large teacher network at the deployment stage. To reduce the necessity of…

Ensemble learning is a very prevalent method employed in machine learning. The relative success of ensemble methods is attributed to their ability to tackle a wide range of instances and complex problems that require different low-level…

As Large Language Models (LLMs) continue to grow in both capability and cost, transferring frontier capabilities into smaller, deployable students has become a central engineering problem, and knowledge distillation remains the dominant…

Large language models are increasingly post-trained with reinforcement learning in verifiable domains such as code and math. Yet, current methods for reinforcement learning with verifiable rewards (RLVR) learn only from a scalar outcome…

Causal effect estimation has been widely used in marketing optimization. The framework of an uplift model followed by a constrained optimization algorithm is popular in practice. To enhance performance in the online environment, the…

Knowledge distillation (KD) is one of the most useful techniques for light-weight neural networks. Although neural networks have a clear purpose of embedding datasets into the low-dimensional space, the existing knowledge was quite far from…

In the zero-shot policy transfer setting in reinforcement learning, the goal is to train an agent on a fixed set of training environments so that it can generalise to similar, but unseen, testing environments. Previous work has shown that…

Ensemble knowledge distillation can extract knowledge from multiple teacher models and encode it into a single student model. Many existing methods learn and distill the student model on labeled data only. However, the teacher models are…

Many applications of reinforcement learning can be formalized as goal-conditioned environments, where, in each episode, there is a "goal" that affects the rewards obtained during that episode but does not affect the dynamics. Various…

Offline reinforcement learning (RL) is challenged by the distributional shift between learning policies and datasets. To address this problem, existing works mainly focus on designing sophisticated algorithms to explicitly or implicitly…

The performance of federated learning in neural networks is generally influenced by the heterogeneity of the data distribution. For a well-performing global model, taking a weighted average of the local models, as done by most existing…

Most meta-learning approaches assume the existence of a very large set of labeled data available for episodic meta-learning of base knowledge. This contrasts with the more realistic continual learning paradigm in which data arrives…

Knowledge distillation (KD) has traditionally relied on a static teacher-student framework, where a large, well-trained teacher transfers knowledge to a single student model. However, these approaches often suffer from knowledge…

The knowledge base in a retrieval-augmented generation (RAG) system is typically assembled once and never revised, even though the facts a query requires are often fragmented across documents and buried in irrelevant content. We argue that…

Large Language Models (LLMs) have shown potential in automatic bundle generation but suffer from prohibitive computational costs. Although knowledge distillation offers a pathway to more efficient student models, our preliminary study…

Knowledge distillation is used, in generative language modeling, to train a smaller student model using the help of a larger teacher model, resulting in improved capabilities for the student model. In this paper, we formulate a more general…

Large-scale contrastive learning models can learn very informative sentence embeddings, but are hard to serve online due to the huge model size. Therefore, they often play the role of "teacher", transferring abilities to small "student"…

Post-training with Reinforcement Learning (RL) has substantially improved reasoning in Large Language Models (LLMs) via test-time scaling. However, extending this paradigm to Multimodal LLMs (MLLMs) through verbose rationales yields limited…

Recent advances of gradient temporal-difference methods allow to learn off-policy multiple value functions in parallel with- out sacrificing convergence guarantees or computational efficiency. This opens up new possibilities for sound…

Deep learning-based speech enhancement (SE) models have recently outperformed traditional techniques, yet their deployment on resource-constrained devices remains challenging due to high computational and memory demands. This paper…