相关论文: Trust Semantics Distillation for Collaborator Sele…

The effective completion of tasks in collaborative systems hinges on task-specific trust evaluations of potential devices for distributed collaboration. Due to independent operation of devices involved, dynamic evolution of their mutual…

Causal language models have demonstrated remarkable capabilities, but their size poses significant challenges for deployment in resource-constrained environments. Knowledge distillation, a widely-used technique for transferring knowledge…

As future tasks in networked systems are increasingly relying on collaborative execution among distributed devices, trust has become an essential tool for securing both reliable collaborators and task-specific resources. However, the…

Layer-wise distillation is a powerful tool to compress large models (i.e. teacher models) into small ones (i.e., student models). The student distills knowledge from the teacher by mimicking the hidden representations of the teacher at…

This paper addresses the challenges of high computational cost and slow inference in deploying large language models. It proposes a distillation strategy guided by multiple teacher models. The method constructs several teacher models and…

Knowledge Distillation (KD) can transfer the reasoning abilities of large models to smaller ones, which can reduce the costs to generate Chain-of-Thoughts for reasoning tasks. KD methods typically ask the student to mimic the teacher's…

Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of teacher confidence. This indiscriminate supervision amplifies…

Many real-world applications such as robotics provide hard constraints on power and compute that limit the viable model complexity of Reinforcement Learning (RL) agents. Similarly, in many distributed RL settings, acting is done on…

Recent studies have focused on leveraging large-scale artificial intelligence (LAI) models to improve semantic representation and compression capabilities. However, the substantial computational demands of LAI models pose significant…

Advances in self-distillation have shown that when knowledge is distilled from a teacher to a student using the same deep learning (DL) architecture, the student performance can surpass the teacher particularly when the network is…

Casting complex inputs into tractable representations is a critical step across various fields. Diverse embedding models emerge from differences in architectures, loss functions, input modalities and datasets, each capturing unique aspects…

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…

The outpouring of various pre-trained models empowers knowledge distillation by providing abundant teacher resources, but there lacks a developed mechanism to utilize these teachers adequately. With a massive model repository composed of…

The success of collaborative task completion among networked devices hinges on the effective selection of trustworthy collaborators. However, accurate task-specific trust evaluation of multi-hop collaborators can be extremely complex. The…

Deep learning has shown its efficacy in extracting useful features to solve various computer vision tasks. However, when the structure of the data is complex and noisy, capturing effective information to improve performance is very…

There is increasing interest in distilling task-specific knowledge from large language models (LLM) to smaller student models. Nonetheless, LLM distillation presents a dual challenge: 1) there is a high cost associated with querying the…

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…

This paper studies the problem of pre-training for small models, which is essential for many mobile devices. Current state-of-the-art methods on this problem transfer the representational knowledge of a large network (as a Teacher) into a…

Rehearsal-based video incremental learning often employs knowledge distillation to mitigate catastrophic forgetting of previously learned data. However, this method faces two major challenges for video task: substantial computing resources…

In this paper, we introduce a novel knowledge distillation approach for the semantic segmentation task. Unlike previous methods that rely on power-trained teachers or other modalities to provide additional knowledge, our approach does not…