Related papers: Uncertainty Guided Global Memory Improves Multi-Ho…
Visual Question Answering (VQA) has emerged as one of the most challenging tasks in artificial intelligence due to its multi-modal nature. However, most existing VQA methods are incapable of handling Knowledge-based Visual Question…
End-to-end task-oriented dialogue is challenging since knowledge bases are usually large, dynamic and hard to incorporate into a learning framework. We propose the global-to-local memory pointer (GLMP) networks to address this issue. In our…
Transformer-based language models (LMs) track contextual information through large, hard-coded input windows. We introduce MemoryPrompt, a leaner approach in which the LM is complemented by a small auxiliary recurrent network that passes…
Memory-augmented large language models extend reasoning beyond a fixed context window by maintaining long-term memory across interactions. However, existing memory systems often collapse stable user facts, episodic events, and behavioral…
Fusion-in-decoder (Fid) (Izacard and Grave, 2020) is a generative question answering (QA) model that leverages passage retrieval with a pre-trained transformer and pushed the state of the art on single-hop QA. However, the complexity of…
Video Question Answering (VideoQA) demands models that jointly reason over spatial, temporal, and linguistic cues. However, the task's inherent complexity often requires multi-step reasoning that current large multimodal models (LMMs)…
Multi-hop Question Answering (QA) is a challenging task since it requires an accurate aggregation of information from multiple context paragraphs and a thorough understanding of the underlying reasoning chains. Recent work in multi-hop QA…
Knowledge graph reasoning plays a vital role in various applications and has garnered considerable attention. Recently, path-based methods have achieved impressive performance. However, they may face limitations stemming from constraints in…
Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…
Reading Comprehension has received significant attention in recent years as high quality Question Answering (QA) datasets have become available. Despite state-of-the-art methods achieving strong overall accuracy, Multi-Hop (MH) reasoning…
Question Answering over Temporal Knowledge Graphs (TKGQA) has attracted growing interest for handling time-sensitive queries. However, existing methods still struggle with: 1) weak incorporation of temporal constraints in question…
Transformers have achieved remarkable success in sequence modeling and beyond but suffer from quadratic computational and memory complexities with respect to the length of the input sequence. Leveraging techniques include sparse and linear…
Question Answering has come a long way from answer sentence selection, relational QA to reading and comprehension. We shift our attention to generative question answering (gQA) by which we facilitate machine to read passages and answer…
Human intention prediction is a growing area of research where an activity in a video has to be anticipated by a vision-based system. To this end, the model creates a representation of the past, and subsequently, it produces future…
Transformer model has been widely used on machine translation tasks and obtained state-of-the-art results. In this paper, we report an interesting phenomenon in its encoder-decoder multi-head attention: different attention heads of the…
Recent progress in generative models has stimulated significant innovations in many fields, such as image generation and chatbots. Despite their success, these models often produce sketchy and misleading solutions for complex multi-agent…
Complex Logical Query Answering (CLQA) over incomplete knowledge graphs is a challenging task. Recently, Query Embedding (QE) methods are proposed to solve CLQA by performing multi-hop logical reasoning. However, most of them only consider…
Language-enabled AI systems can answer complex, multi-hop questions to high accuracy, but supporting answers with evidence is a more challenging task which is important for the transparency and trustworthiness to users. Prior work in this…
Large Language Models (LLMs) excel in many natural language processing tasks but often exhibit factual inconsistencies in knowledge-intensive settings. Integrating external knowledge resources, particularly knowledge graphs (KGs), provides…
The transformer is the most popular neural architecture for language modeling. The cornerstone of the transformer is its global attention mechanism, which lets the model aggregate information from all preceding tokens before generating the…