Related papers: Uncertainty Guided Global Memory Improves Multi-Ho…

Transformers have become the dominant architecture across a wide range of domains, largely due to the effectiveness of multi-head attention in capturing diverse representation subspaces. However, standard multi-head attention activates all…

Recently, radical progress in machine learning (ML) has revolutionized computational materials science, enabling unprecedentedly rapid materials discovery and property prediction, but the quantum many-body problem -- which is the key to…

Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context…

This paper proposes a group deliberation oriented multi-agent conversational model to address the limitations of single large language models in complex reasoning tasks. The model adopts a three-level role division architecture consisting…

Many visual scenes contain text that carries crucial information, and it is thus essential to understand text in images for downstream reasoning tasks. For example, a deep water label on a warning sign warns people about the danger in the…

In recent years, the use of large language models (LLMs) has significantly increased, and these models have demonstrated remarkable performance in a variety of general language tasks. However, the evaluation of their performance in…

Human state recognition is a critical topic with pervasive and important applications in human-machine systems. Multi-modal fusion, the combination of metrics from multiple data sources, has been shown as a sound method for improving the…

Transformers have become the go-to architecture for language and vision tasks, yet their theoretical properties, especially memorization capacity, remain elusive. This paper investigates the memorization abilities of multi-head attention…

The quadratic computational and memory complexities of large Transformers have limited their scalability for long document summarization. In this paper, we propose Hepos, a novel efficient encoder-decoder attention with head-wise positional…

Natural language understanding tasks such as open-domain question answering often require retrieving and assimilating factual information from multiple sources. We propose to address this problem by integrating a semi-parametric…

Transformer is a powerful model for text understanding. However, it is inefficient due to its quadratic complexity to input sequence length. Although there are many methods on Transformer acceleration, they are still either inefficient on…

As large language models increasingly gain popularity in real-world applications, processing extremely long contexts, often exceeding the model's pre-trained context limits, has emerged as a critical challenge. While existing approaches to…

Multimodal trajectory prediction generates multiple plausible future trajectories to address vehicle motion uncertainty from intention ambiguity and execution variability. However, HD map-dependent models suffer from costly data…

Transformers have emerged as the underpinning architecture for Large Language Models (LLMs). In generative language models, the inference process involves two primary phases: prompt processing and token generation. Token generation, which…

Domain-specific question answering (QA) systems for services face unique challenges in integrating heterogeneous knowledge sources while ensuring both accuracy and safety. Existing large language models often struggle with factual…

Speech-driven 3D facial animation is challenging due to the complex geometry of human faces and the limited availability of 3D audio-visual data. Prior works typically focus on learning phoneme-level features of short audio windows with…

Multi-hop Question Answering over Knowledge Graph~(KGQA) aims to find the answer entities that are multiple hops away from the topic entities mentioned in a natural language question on a large-scale Knowledge Graph (KG). To cope with the…

Reinforcement learning has recently shown promise in improving retrieval-augmented generation (RAG). Despite these advances, its effectiveness in multi-hop question answering (QA) remains limited by two fundamental limitations: (i) global…

Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries. Yet, most LLM systems rely on full-context prompting,…

Multi-hop question generation (MQG) aims to generate complex questions which require reasoning over multiple pieces of information of the input passage. Most existing work on MQG has focused on exploring graph-based networks to equip the…