Related papers: Selective Token Generation for Few-shot Natural La…
Time series data is fundamental to decision-making across many domains including healthcare, finance, power systems, and logistics. However, analyzing this data correctly often requires incorporating unstructured contextual information,…
ASR error correction is an interesting option for post processing speech recognition system outputs. These error correction models are usually trained in a supervised fashion using the decoding results of a target ASR system. This approach…
In the last decade, a considerable research effort has been devoted to developing adaptive algorithms based on kernel functions. One of the main features of these algorithms is that they form a family of universal approximation techniques,…
Large pre-trained language models (LLMs) have been shown to have significant potential in few-shot learning across various fields, even with minimal training data. However, their ability to generalize to unseen tasks in more complex fields,…
We present SkillNet-NLG, a sparsely activated approach that handles many natural language generation tasks with one model. Different from traditional dense models that always activate all the parameters, SkillNet-NLG selectively activates…
Neural Transfer Learning (TL) is becoming ubiquitous in Natural Language Processing (NLP), thanks to its high performance on many tasks, especially in low-resourced scenarios. Notably, TL is widely used for neural domain adaptation to…
Retrieval-augmented generation (RAG) systems empower large language models (LLMs) to access external knowledge during inference. Recent advances have enabled LLMs to act as search agents via reinforcement learning (RL), improving…
Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality. Most NLG systems in common use employ rules and heuristics and tend to generate rigid and…
Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…
The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing efficiency methods mainly target inference via token reduction or merging, offering limited benefits…
Using large language models, this paper presents techniques to improve extremely low-resourced indigenous language translations. Our approaches are grounded in the use of (1) the presence of a datastore consisting of a limited number of…
Few-shot text classification aims to classify the text under the few-shot scenario. Most of the previous methods adopt optimization-based meta learning to obtain task distribution. However, due to the neglect of matching between the few…
Goal-conditioned and Multi-Task Reinforcement Learning (GCRL and MTRL) address numerous problems related to robot learning, including locomotion, navigation, and manipulation scenarios. Recent works focusing on language-defined robotic…
Recent studies have uncovered the potential of Large Language Models (LLMs) in addressing complex sequential decision-making tasks through the provision of high-level instructions. However, LLM-based agents lack specialization in tackling…
Memory, additional information beyond the training of large language models (LLMs), is crucial to various real-world applications, such as personal assistant. The two mainstream solutions to incorporate memory into the generation process…
Recommender systems utilizing explicit feedback have witnessed significant advancements and widespread applications over the past years. However, generating recommendations in few-shot scenarios remains a persistent challenge. Recently,…
The remarkable performance of large language models (LLMs) in zero-shot language understanding has garnered significant attention. However, employing LLMs for large-scale inference or domain-specific fine-tuning requires immense…
Pre-trained language models (PLMs) have exhibited remarkable few-shot learning capabilities when provided a few examples in a natural language prompt as demonstrations of test instances, i.e., in-context learning. However, the performance…
Large pretrained models are showing increasingly better performance in reasoning and planning tasks across different modalities, opening the possibility to leverage them for complex sequential decision making problems. In this paper, we…
Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of this technique hinges on the trade-off between the time…