Related papers: Decoupling Knowledge from Memorization: Retrieval-…
Large pre-trained vision-language models like CLIP have shown great potential in learning representations that are transferable across a wide range of downstream tasks. Different from the traditional representation learning that is based…
Prompt learning has achieved great success in efficiently exploiting large-scale pre-trained models in natural language processing (NLP). It reformulates the downstream tasks as the generative pre-training ones to achieve consistency, thus…
Masked language models like BERT can perform text classification in a zero-shot fashion by reformulating downstream tasks as text infilling. However, this approach is highly sensitive to the template used to prompt the model, yet…
Pretrained biomedical vision-language models (VLMs) such as BioMedCLIP perform well on average but often degrade on challenging modalities where inter-class margins are small and acquisition-specific variations are pronounced, especially…
Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve state-of-the-art performance, which however are prone to…
We propose a novel memory-modular learner for image classification that separates knowledge memorization from reasoning. Our model enables effective generalization to new classes by simply replacing the memory contents, without the need for…
Deep pretrained language models have achieved great success in the way of pretraining first and then fine-tuning. But such a sequential transfer learning paradigm often confronts the catastrophic forgetting problem and leads to sub-optimal…
Language models, especially pre-trained large language models, have showcased remarkable abilities as few-shot in-context learners (ICL), adept at adapting to new tasks with just a few demonstrations in the input context. However, the…
RNN-like language models are getting renewed attention from NLP researchers in recent years and several models have made significant progress, which demonstrates performance comparable to traditional transformers. However, due to the…
The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge. Typical methods rely on a rehearsal buffer or known task…
Prompt Recovery, reconstructing prompts from the outputs of large language models (LLMs), has grown in importance as LLMs become ubiquitous. Most users access LLMs through APIs without internal model weights, relying only on outputs and…
Petroni et al. (2019) demonstrated that it is possible to retrieve world facts from a pre-trained language model by expressing them as cloze-style prompts and interpret the model's prediction accuracy as a lower bound on the amount of…
Recently, a boom of papers has shown extraordinary progress in zero-shot and few-shot learning with various prompt-based models. It is commonly argued that prompts help models to learn faster in the same way that humans learn faster when…
The ability of machine learning systems to learn continually is hindered by catastrophic forgetting, the tendency of neural networks to overwrite previously acquired knowledge when learning a new task. Existing methods mitigate this problem…
Conversational query rewriting is crucial for effective conversational search, yet traditional supervised methods require substantial labeled data, which is scarce in low-resource settings. This paper introduces Prompt-Guided In-Context…
Prompting pre-trained language models leads to promising results across natural language processing tasks but is less effective when applied in low-resource domains, due to the domain gap between the pre-training data and the downstream…
Few-shot action recognition in videos is challenging for its lack of supervision and difficulty in generalizing to unseen actions. To address this task, we propose a simple yet effective method, called knowledge prompting, which leverages…
Prompt tuning has become a popular strategy for adapting Vision-Language Models (VLMs) to zero/few-shot visual recognition tasks. Some prompting techniques introduce prior knowledge due to its richness, but when learnable tokens are…
Multimodal Continual Instruction Tuning (MCIT) enables Multimodal Large Language Models (MLLMs) to meet continuously emerging requirements without expensive retraining. MCIT faces two major obstacles: catastrophic forgetting (where old…
Recent studies have shown that Large Language Models (LLMs) can improve their reasoning performance through self-generated few-shot examples, achieving results comparable to manually curated in-context examples. However, the underlying…