Related papers: DisTaC: Conditioning Task Vectors via Distillation…
In this paper, we propose that small models may not need to absorb the cost of pre-training to reap its benefits. Instead, they can capitalize on the astonishing results achieved by modern, enormous models to a surprising degree. We observe…
In feeds recommendation, the first step is candidate generation. Most of the candidate generation models are based on CTR estimation, which do not consider user's satisfaction with the clicked item. Items with low quality but attractive…
Knowledge distillation transfers knowledge from a large model to a small one via task and distillation losses. In this paper, we observe a trade-off between task and distillation losses, i.e., introducing distillation loss limits the…
Knowledge distillation is a powerful method for model compression, enabling the efficient deployment of complex deep learning models (teachers), including large language models. However, its underlying statistical mechanisms remain unclear,…
In multi-task reinforcement learning there are two main challenges: at training time, the ability to learn different policies with a single model; at test time, inferring which of those policies applying without an external signal. In the…
Data-centric distillation, including data augmentation, selection, and mixing, offers a promising path to creating smaller, more efficient student Large Language Models (LLMs) that retain strong reasoning abilities. However, there still…
Robust multimodal human sensing must overcome the critical challenge of missing modalities. Two principal barriers are the Representation Gap between heterogeneous data and the Contamination Effect from low-quality modalities. These…
Knowledge distillation as an efficient knowledge transfer technique, has achieved remarkable success in unimodal scenarios. However, in cross-modal settings, conventional distillation methods encounter significant challenges due to data and…
Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning,…
In this paper, we argue about the importance of considering task interactions at multiple scales when distilling task information in a multi-task learning setup. In contrast to common belief, we show that tasks with high affinity at a…
Image diffusion distillation achieves high-fidelity generation with very few sampling steps. However, applying these techniques directly to video diffusion often results in unsatisfactory frame quality due to the limited visual quality in…
Changing how pre-trained models behave -- e.g., improving their performance on a downstream task or mitigating biases learned during pre-training -- is a common practice when developing machine learning systems. In this work, we propose a…
The huge size of the widely used BERT family models has led to recent efforts about model distillation. The main goal of distillation is to create a task-agnostic pre-trained model that can be fine-tuned on downstream tasks without…
Graph convolutional networks have made great progress in graph-based semi-supervised learning. Existing methods mainly assume that nodes connected by graph edges are prone to have similar attributes and labels, so that the features smoothed…
Deep learning based models are relatively large, and it is hard to deploy such models on resource-limited devices such as mobile phones and embedded devices. One possible solution is knowledge distillation whereby a smaller model (student…
Knowledge distillation addresses the problem of transferring knowledge from a teacher model to a student model. In this process, we typically have multiple types of knowledge extracted from the teacher model. The problem is to make full use…
Knowledge distillation is a potential solution for model compression. The idea is to make a small student network imitate the target of a large teacher network, then the student network can be competitive to the teacher one. Most previous…
Deep learning methods usually require a large amount of training data and lack interpretability. In this paper, we propose a novel knowledge distillation and model interpretation framework for medical image classification that jointly…
Diffusion Transformers (DiTs) have demonstrated strong performance in generative modeling, particularly in image synthesis, making them a compelling choice for molecular conformer generation. However, applying DiTs to molecules introduces…
Mixing datasets for fine-tuning large models (LMs) has become critical for maximizing performance on downstream tasks. However, composing effective dataset mixtures typically relies on heuristics and trial-and-error, often requiring…