Related papers: X-Token: Projection-Guided Cross-Tokenizer Knowled…
With ever growing scale of neural models, knowledge distillation (KD) attracts more attention as a prominent tool for neural model compression. However, there are counter intuitive observations in the literature showing some challenging…
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…
On-policy distillation (OPD) is a standard tool for transferring teacher behavior to a smaller student, but it implicitly assumes that teacher and student predictions are comparable token by token, an assumption that fails whenever the two…
Knowledge distillation is a popular technique for training a small student network to emulate a larger teacher model, such as an ensemble of networks. We show that while knowledge distillation can improve student generalization, it does not…
Multi-task learning (MTL) is to learn one single model that performs multiple tasks for achieving good performance on all tasks and lower cost on computation. Learning such a model requires to jointly optimize losses of a set of tasks with…
We propose a resource-efficient framework for compressing large language models through knowledge distillation, combined with guided chain-of-thought reinforcement learning. Using Qwen 3B as the teacher and Qwen 0.5B as the student, we…
Vision Language Models (VLMs), pre-trained on large-scale image-text datasets, enable zero-shot predictions for unseen data but may underperform on specific unseen tasks. Continual learning (CL) can help VLMs effectively adapt to new data…
In the knowledge distillation literature, feature-based methods have dominated due to their ability to effectively tap into extensive teacher models. In contrast, logit-based approaches, which aim to distill "dark knowledge" from teachers,…
Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model. Previous KD methods typically train a student by minimizing a task-related loss and…
Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are misaligned with the dynamic learning process of student…
Temporal knowledge graphs (TKGs) support reasoning over time-evolving facts, yet state-of-the-art models are often computationally heavy and costly to deploy. Existing compression and distillation techniques are largely designed for static…
Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, in the context of autoregressive language models (LMs), we…
Knowledge distillation (KD) is an efficient approach to transfer the knowledge from a large "teacher" network to a smaller "student" network. Traditional KD methods require lots of labeled training samples and a white-box teacher…
Knowledge distillation is a technique to enhance the generalization ability of a student model by exploiting outputs from a teacher model. Recently, feature-map based variants explore knowledge transfer between manually assigned…
Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, which is very successful in multi-class single-label learning.…
Knowledge Distillation (KD) for Large Language Models (LLMs) has become increasingly important as models grow in size and complexity. While existing distillation approaches focus on imitating teacher behavior, they often overlook the…
Pretrained language models have led to significant performance gains in many NLP tasks. However, the intensive computing resources to train such models remain an issue. Knowledge distillation alleviates this problem by learning a…
Knowledge distillation is a widely applicable technique for training a student neural network under the guidance of a trained teacher network. For example, in neural network compression, a high-capacity teacher is distilled to train a…
Deep neural models in recent years have been successful in almost every field, including extremely complex problem statements. However, these models are huge in size, with millions (and even billions) of parameters, thus demanding more…
Despite the impressive performance achieved by data-fusion networks with duplex encoders for visual semantic segmentation, they become ineffective when spatial geometric data are not available. Implicitly infusing the spatial geometric…