相关论文: Bidirectional Attention as a Mixture of Continuous…

In-context learning with attention enables large neural networks to make context-specific predictions by selectively focusing on relevant examples. Here, we adapt this idea to supervised learning procedures such as lasso regression and…

Multimodal large language models (MLLMs), initiated with a trained LLM, first align images with text and then fine-tune on multimodal mixed inputs. However, the MLLM catastrophically forgets the text-only instructions, which do not include…

Attention mechanisms are critical to the success of large language models (LLMs), driving significant advancements in multiple fields. However, for graph-structured data, which requires emphasis on topological connections, they fall short…

To enhance the efficiency of the attention mechanism within large language models (LLMs), previous works primarily compress the KV cache or group attention heads, while largely overlooking redundancy between layers. Our comprehensive…

Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamental obstacle to efficient long-context modeling. To address…

Word embeddings, which represent a word as a point in a vector space, have become ubiquitous to several NLP tasks. A recent line of work uses bilingual (two languages) corpora to learn a different vector for each sense of a word, by…

With the aim of promoting and understanding the multilingual version of image search, we leverage visual object detection and propose a model with diverse multi-head attention to learn grounded multilingual multimodal representations.…

Interacting with humans through multi-turn conversations is a fundamental feature of large language models (LLMs). However, existing LLM serving engines executing multi-turn conversations are inefficient due to the need to repeatedly…

The reasoning pattern of Large language models (LLMs) remains opaque, and Reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work…

Large language models (LLMs) have shown impressive few-shot generalization on many tasks via in-context learning (ICL). Despite their success in showing such emergent abilities, the scale and complexity of larger models also lead to…

Antibody binding site prediction plays a pivotal role in computational immunology and therapeutic antibody design. Existing sequence or structure methods rely on single-view features and fail to identify antibody-specific binding sites on…

Multimodal Language Analysis is a demanding area of research, since it is associated with two requirements: combining different modalities and capturing temporal information. During the last years, several works have been proposed in the…

An LLM's residual stream is both state and instruction: it encodes the current context and determines the next transformation. We introduce a parameter-free decomposition for Mixture-of-Experts models that splits each layer's hidden state…

Decoder-only large language models (LLMs) have been increasingly adopted to build embedding models for diverse tasks. To overcome the inherent limitations of causal attention in representation learning, many existing methods modify the…

The rapid adoption of Mixture-of-Experts (MoE) architectures marks a major shift in the deployment of Large Language Models (LLMs). MoE LLMs improve scaling efficiency by activating only a small subset of parameters per token, but their…

Mixture-of-Experts (MoE) models enable efficient scaling of large language models (LLMs) by activating only a subset of experts per input. However, we observe that the commonly used auxiliary load balancing loss often leads to expert…

In this study, we propose a novel multi-modal end-to-end neural approach for automated assessment of non-native English speakers' spontaneous speech using attention fusion. The pipeline employs Bi-directional Recurrent Convolutional Neural…

In a multilingual neural machine translation model that fully shares parameters across all languages, an artificial language token is usually used to guide translation into the desired target language. However, recent studies show that…

Word embedding is central to neural machine translation (NMT), which has attracted intensive research interest in recent years. In NMT, the source embedding plays the role of the entrance while the target embedding acts as the terminal.…

Attention layers are widely used in natural language processing (NLP) and are beginning to influence computer vision architectures. Training very large transformer models allowed significant improvement in both fields, but once trained,…