Related papers: KAT: A Knowledge Augmented Transformer for Vision-…

Recent advancements in AI reasoning have driven substantial improvements across diverse tasks. A critical open question is whether these improvements also yields better knowledge transfer: the ability of models to communicate reasoning in…

Autoregressive large language models (LLMs) pre-trained by next token prediction are inherently proficient in generative tasks. However, their performance on knowledge-driven tasks such as factual knowledge querying remains unsatisfactory.…

One of the key factors in language productivity and human cognition is the ability of systematic compositionality, which refers to understanding composed unseen examples of seen primitives. However, recent evidence reveals that the…

Reasoning over multiple modalities, e.g. in Visual Question Answering (VQA), requires an alignment of semantic concepts across domains. Despite the widespread success of end-to-end learning, today's multimodal pipelines by and large…

The superior performance of deep learning relies heavily on a large collection of sample data, but the data insufficiency problem turns out to be relatively common in global electricity markets. How to prevent overfitting in this case…

Recently, large language models (LLMs) have gained much attention for the emergence of human-comparable capabilities and huge potential. However, for open-domain implicit question-answering problems, LLMs may not be the ultimate solution…

Contextual word representations, typically trained on unstructured, unlabeled text, do not contain any explicit grounding to real world entities and are often unable to remember facts about those entities. We propose a general method to…

Knowledge-based Visual Question Answering (KVQA) requires external knowledge beyond the visible content to answer questions about an image. This ability is challenging but indispensable to achieve general VQA. One limitation of existing…

Recent advances in Multimodal Large Language Models (MLLMs) have shown impressive reasoning capabilities across vision-language tasks, yet still face the challenge of compute-difficulty mismatch. Through empirical analyses, we identify that…

Answering complex questions is a challenging task that requires question decomposition and multistep reasoning for arriving at the solution. While existing supervised and unsupervised approaches are specialized to a certain task and involve…

Retrieval-augmented generation (RAG) enables large language models (LLMs) to dynamically access external information, which is powerful for answering questions over previously unseen documents. Nonetheless, they struggle with high-level…

Large language models (LLMs) have recently been applied to dialog systems. Despite making progress, LLMs are prone to errors in knowledge-intensive scenarios. Recently, approaches based on retrieval augmented generation (RAG) and agent have…

Integrating outside knowledge for reasoning in visio-linguistic tasks such as visual question answering (VQA) is an open problem. Given that pretrained language models have been shown to include world knowledge, we propose to use a unimodal…

There has been a growing interest in solving Visual Question Answering (VQA) tasks that require the model to reason beyond the content present in the image. In this work, we focus on questions that require commonsense reasoning. In contrast…

Knowledge-aware question answering (KAQA) requires the model to answer questions over a knowledge base, which is essential for both open-domain QA and domain-specific QA, especially when language models alone cannot provide all the…

Knowledge-based visual question answering (KB-VQA) is a challenging task, which requires the model to leverage external knowledge for comprehending and answering questions grounded in visual content. Recent studies retrieve the knowledge…

We present Knowledge Enhanced Multimodal BART (KM-BART), which is a Transformer-based sequence-to-sequence model capable of reasoning about commonsense knowledge from multimodal inputs of images and texts. We adapt the generative BART…

Recent work on enhancing BERT-based language representation models with knowledge graphs (KGs) and knowledge bases (KBs) has yielded promising results on multiple NLP tasks. State-of-the-art approaches typically integrate the original input…

Repository-level code comprehension and knowledge sharing remain core challenges in software engineering. Large language models (LLMs) have shown promise by generating explanations of program structure and logic. However, these approaches…

A significant challenge in machine learning, particularly in noisy and low-data environments, lies in effectively incorporating inductive biases to enhance data efficiency and robustness. Despite the success of informed machine learning…