Related papers: TiTok: Transfer Token-level Knowledge via Contrast…
Continual incorporation of new knowledge is essential for the long-term evolution of large language models (LLMs). Existing approaches typically rely on parameter-update algorithms to mitigate catastrophic forgetting, yet they suffer from…
Transfer learning on tabular data is challenging due to disparate feature spaces across domains, in contrast to the homogeneous structures of image and text. Large language models (LLMs) offer a knowledge base to improve the limited…
Recent advancements in Large Language Models (LLMs) have emphasized the critical role of fine-tuning (FT) techniques in adapting LLMs to specific tasks, especially when retraining from scratch is computationally infeasible. Fine-tuning…
LoRA has become a universal Parameter-Efficient Fine-Tuning (PEFT) technique that equips Large Language Models (LLMs) to adapt quickly to new tasks. However, when these models are scaled up, even the latest LoRA variants still introduce…
Cross-capability transfer is a key challenge in large language model (LLM) research, with applications in multi-task integration, model compression, and continual learning. Recent works like FuseLLM and FuseChat have demonstrated the…
Recent literature on fine-tuning Large Language Models highlights a fundamental debate. While Full Fine-Tuning (FFT) provides the representational plasticity required for high-entropy knowledge injection, Low-Rank Adaptation (LoRA) can…
Despite remarkable advances in natural language processing, developing effective systems for low-resource languages remains a formidable challenge, with performances typically lagging far behind high-resource counterparts due to data…
Knowledge distillation from pretrained visual representation models offers an effective approach to improve small, task-specific production models. However, the effectiveness of such knowledge transfer drops significantly when distilling…
Supervised fine-tuning (SFT) is the predominant method for adapting large language models (LLMs), yet it often struggles with generalization compared to reinforcement learning (RL). In this work, we posit that this performance disparity…
Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and Parameter-Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting LLMs to downstream tasks.…
Fine-tuning is widely used to tailor large language models for specific tasks such as neural machine translation (NMT). However, leveraging transfer learning is computationally expensive when fine-tuning large multilingual models with…
Large language models can now be personalised efficiently at scale using parameter efficient finetuning methods (PEFTs), but serving user-specific PEFTs harms throughput, even with specialised kernels and memory management techniques. This…
Quantization is an indispensable technique for serving Large Language Models (LLMs) and has recently found its way into LoRA fine-tuning. In this work we focus on the scenario where quantization and LoRA fine-tuning are applied together on…
Large language models (LLMs) have demonstrated remarkable performance across various downstream tasks. However, the high computational and memory requirements of LLMs are a major bottleneck. To address this, parameter-efficient fine-tuning…
Accurate and effective discrete image tokenization is crucial for long image sequence processing. However, current methods rigidly compress all content at a fixed rate, ignoring the variable information density of images and leading to…
Large language models are increasingly adopted as semantic backbones for neural text-to-speech systems. However, frozen LLM representations are insufficient for modeling speaker specific acoustic and perceptual characteristics. Our…
Tabular data are crucial in many fields and their understanding by large language models (LLMs) under high parameter efficiency paradigm is important. However, directly applying parameter-efficient fine-tuning (PEFT) techniques to tabular…
Supervised fine-tuning (SFT) provides the standard approach for teaching LLMs new behaviors from offline expert demonstrations. However, standard SFT uniformly fits all samples -- including those with low likelihood under the base model --…
Knowledge distillation (KD) has been a predominant method for compressing Large Language Models (LLMs). In this paper, we first revisit KD and Low-Rank Adaption (LoRA) and demonstrate that they follow the same paradigm. Inspired by this…
Due to the high memory and computational costs associated with large language models (LLMs), model compression techniques such as quantization, which reduces inference costs, and parameter-efficient fine-tuning (PEFT) methods like Low-Rank…