Related papers: Class Distillation with Mahalanobis Contrast: An E…

Large language models (LLMs) deliver remarkable performance but are costly to deploy, motivating knowledge distillation (KD) for efficient inference. Existing KD objectives typically match student and teacher probabilities via softmax,…

Semantic Textual Similarity (STS) is a crucial component of many Natural Language Processing (NLP) applications. However, existing approaches typically reduce semantic nuances to a single score, limiting interpretability. To address this,…

In the realm of Adversarial Distillation (AD), strategic and precise knowledge transfer from an adversarially robust teacher model to a less robust student model is paramount. Our Dynamic Guidance Adversarial Distillation (DGAD) framework…

Deep neural networks have achieved impressive performance across a wide range of tasks, but this success often comes with substantial computational and storage costs due to large-scale training data. Dataset distillation addresses this…

Recent work has shown that augmenting environments with language descriptions improves policy learning. However, for environments with complex language abstractions, learning how to ground language to observations is difficult due to…

Knowledge Distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model. While contrastive learning has shown promise in self-supervised learning by creating discriminative representations, its…

This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a base model to…

Speech denoising is a generally adopted and impactful task, appearing in many common and everyday-life use cases. Although there are very powerful methods published, most of those are too complex for deployment in everyday and low-resources…

In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting…

Knowledge Distillation (KD) is a critical tool for training Large Language Models (LLMs), yet the majority of research focuses on approaches that rely solely on output logits, neglecting semantic information in the teacher's intermediate…

Large-scale self-supervised pre-trained speech encoders outperform conventional approaches in speech recognition and translation tasks. Due to the high cost of developing these large models, building new encoders for new tasks and deploying…

A huge number of multi-participant dialogues happen online every day, which leads to difficulty in understanding the nature of dialogue dynamics for both humans and machines. Dialogue disentanglement aims at separating an entangled dialogue…

Class-incremental fault diagnosis requires a model to adapt to new fault classes while retaining previous knowledge. However, limited research exists for imbalanced and long-tailed data. Extracting discriminative features from few-shot…

Existing knowledge distillation methods mostly focus on distillation of teacher's prediction and intermediate activation. However, the structured representation, which arguably is one of the most critical ingredients of deep models, is…

Reinforcement learning (RL) can be used to improve the policy (denoiser) of diffusion large language models (dLLMs), while being hindered by the intractability of the policy likelihood. A dominant and efficient family of methods replaces…

Large language models (LLMs) are increasingly deployed worldwide, yet their safety alignment remains predominantly English-centric. This allows for vulnerabilities in non-English contexts, especially with low-resource languages. We…

Although the vision-and-language pretraining (VLP) equipped cross-modal image-text retrieval (ITR) has achieved remarkable progress in the past two years, it suffers from a major drawback: the ever-increasing size of VLP models restricts…

The deployment and application of Large Language Models (LLMs) is hindered by their memory inefficiency, computational demands, and the high costs of API inferences. Traditional distillation methods, which transfer the capabilities of LLMs…

We propose Reinforcement Learning from Contrastive Distillation (RLCD), a method for aligning language models to follow principles expressed in natural language (e.g., to be more harmless) without using human feedback. RLCD creates…

Discrete diffusion models (DDMs) have shown powerful generation ability for discrete data modalities like text and molecules. However, their practical application is hindered by inefficient sampling, requiring a large number of sampling…