相关论文: Diversity-Aware Reverse Kullback-Leibler Divergenc…

In recent years, large language models (LLMs) have shown exceptional capabilities across various natural language processing (NLP) tasks. However, such impressive performance often comes with the trade-off of an increased parameter size,…

The recommendation of medication is a vital aspect of intelligent healthcare systems, as it involves prescribing the most suitable drugs based on a patient's specific health needs. Unfortunately, many sophisticated models currently in use…

In real-world NLP applications, Large Language Models (LLMs) offer promising solutions due to their extensive training on vast datasets. However, the large size and high computation demands of LLMs limit their practicality in many…

Large Language Models (LLMs) have displayed remarkable performances across various complex tasks by leveraging Chain-of-Thought (CoT) prompting. Recently, studies have proposed a Knowledge Distillation (KD) approach, reasoning distillation,…

Very deep models for speaker recognition (SR) have demonstrated remarkable performance improvement in recent research. However, it is impractical to deploy these models for on-device applications with constrained computational resources. On…

Multimodal fake news detection is crucial for mitigating societal disinformation. Existing approaches attempt to address this by fusing multimodal features or leveraging Large Language Models (LLMs) for advanced reasoning. However, these…

Knowledge distillation is central to LLM post-training, yet its design space remains poorly understood, especially alongside reinforcement learning (RL). We show that the prevailing paradigms, off-policy distillation and on-policy…

Despite exciting progress in pre-training for visual-linguistic (VL) representations, very few aspire to a small VL model. In this paper, we study knowledge distillation (KD) to effectively compress a transformer-based large VL model into a…

Diffusion Large Language Models (DLLMs) have emerged as a powerful alternative to autoregressive models, enabling parallel token generation across multiple positions. However, preference alignment of DLLMs remains challenging due to high…

Reasoning distillation aims to transfer multi-step reasoning capabilities from large language models to smaller, more efficient ones. While recent methods have shown promising gains, they typically rely on static teacher-student hierarchies…

Ensembles of machine learning models yield improved system performance as well as robust and interpretable uncertainty estimates; however, their inference costs may often be prohibitively high. \emph{Ensemble Distribution Distillation} is…

Self-supervised methods have gained prominence in time series anomaly detection due to the scarcity of available annotations. Nevertheless, they typically demand extensive training data to acquire a generalizable representation map, which…

Owing to their powerful semantic reasoning capabilities, Large Language Models (LLMs) have been effectively utilized as recommenders, achieving impressive performance. However, the high inference latency of LLMs significantly restricts…

Knowledge distillation (KD) is a widely adopted approach for compressing large neural networks by transferring knowledge from a large teacher model to a smaller student model. In the context of large language models, token level KD,…

Knowledge distillation (KD) has become an important technique for model compression and knowledge transfer. In this work, we first perform a comprehensive analysis of the knowledge transferred by different KD methods. We demonstrate that…

Knowledge distillation (KD) is a key technique for compressing large language models into smaller ones while preserving performance. Despite the recent traction of KD research, its effectiveness for smaller language models (LMs) and the…

Large language models (LLMs) provide a promising way for accurate session-based recommendation (SBR), but they demand substantial computational time and memory. Knowledge distillation (KD)-based methods can alleviate these issues by…

Diffusion models have emerged as a powerful paradigm for modern generative modeling, demonstrating strong potential for large language models (LLMs). Unlike conventional autoregressive (AR) models that generate tokens sequentially,…

Alignment techniques enable Large Language Models (LLMs) to generate outputs that align with human preferences and play a crucial role in their effectiveness. However, their impact often diminishes when applied to Small Language Models…

The upscaling of Large Language Models (LLMs) has yielded impressive advances in natural language processing, yet it also poses significant deployment challenges. Weight quantization has emerged as a widely embraced solution to reduce…