Related papers: Typologically Informed Parameter Aggregation
With the advent of large-scale pre-trained models, interest in adapting and exploiting them for continual learning scenarios has grown. In this paper, we propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that…
This paper explores the task of leveraging typology in the context of cross-lingual dependency parsing. While this linguistic information has shown great promise in pre-neural parsing, results for neural architectures have been mixed. The…
Although scaling up the number of trainable parameters in both pre-training and fine-tuning can effectively improve the performance of large language models, it also leads to increased computational overhead. When delving into the parameter…
Curating datasets that span multiple languages is challenging. To make the collection more scalable, researchers often incorporate one or more imperfect classifiers in the process, like language identification models. These models, however,…
The performance of Large Language Models (LLMs) is increasingly governed by data efficiency rather than raw scaling volume. However, existing selection methods often decouple global distribution balancing from local instance selection,…
Providing natural language instructions in prompts is a useful new paradigm for improving task performance of large language models in a zero-shot setting. Recent work has aimed to improve such prompts via manual rewriting or gradient-based…
Mechanisms for continued self-improvement of language models without external supervision remain an open challenge. We propose Peer-Predictive Self-Training (PST), a label-free fine-tuning framework in which multiple language models improve…
Answering complex logical queries on incomplete knowledge graphs (KGs) is a fundamental and challenging task in multi-hop reasoning. Recent work defines this task as an end-to-end optimization problem, which significantly reduces the…
With excellent generalization ability, self-supervised speech models have shown impressive performance on various downstream speech tasks in the pre-training and fine-tuning paradigm. However, as the growing size of pre-trained models,…
Multilingual models, such as M-BERT and XLM-R, have gained increasing popularity, due to their zero-shot cross-lingual transfer learning capabilities. However, their generalization ability is still inconsistent for typologically diverse…
The widespread utilization of language models in modern applications is inconceivable without Parameter-Efficient Fine-Tuning techniques, such as low-rank adaptation ($\texttt{LoRA}$), which adds trainable adapters to selected layers.…
Textual adapter-based tuning methods have shown significant potential in transferring knowledge from pre-trained Vision-Language Models (VLMs) to downstream tasks. Existing works generally employ the deterministic textual feature adapter to…
With the advancement of large pre-trained vision-language models, effectively transferring the knowledge embedded within these foundational models to downstream tasks has become a pivotal topic, particularly in data-scarce environments.…
Combining pre-trained expert models offers substantial potential for scalable multimodal reasoning, but building a unified framework remains challenging due to the increasing diversity of input modalities and task complexity. For instance,…
Various algorithms for text-independent speaker recognition have been developed through the decades, aiming to improve both accuracy and efficiency. This paper presents a novel PCA/LDA-based approach that is faster than traditional…
Pre-trained vision-language models (e.g., CLIP) have shown promising zero-shot generalization in many downstream tasks with properly designed text prompts. Instead of relying on hand-engineered prompts, recent works learn prompts using the…
Neural networks have shown substantial promise at automatic theorem-proving in interactive proof assistants (ITPs) like Lean and Coq. However, most neural theorem-proving models are restricted to specific ITPs, leaving out opportunities for…
Pretrained vision-language models (VLMs), such as CLIP, achieve remarkable zero-shot performance, yet their downstream potential hinges on effective fine-tuning. Most adaptation methods typically focus on refining representation from…
Low-rank adapters enable fine-tuning of large models with only a small number of parameters, thus reducing storage costs and minimizing the risk of catastrophic forgetting. However, they often pose optimization challenges, with poor…
Large pre-trained vision-language models, such as CLIP, have demonstrated state-of-the-art performance across a wide range of image classification tasks, without requiring retraining. Few-shot CLIP is competitive with existing specialized…