Search Results for author:
Found 16 papers, 12 papers with code
Harder Tasks Need More Experts: Dynamic Routing in MoE Models
In this paper, we introduce a novel dynamic expert selection framework for Mixture of Experts (MoE) models, aiming to enhance computational efficiency and model performance by adjusting the number of activated experts based on input difficulty.
Probing Multimodal Large Language Models for Global and Local Semantic Representations
The advancement of Multimodal Large Language Models (MLLMs) has greatly accelerated the development of applications in understanding integrated texts and images.
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos.
Ranked #63 on
Visual Question Answering
on MM-Vet
Relation-Aware Question Answering for Heterogeneous Knowledge Graphs
To address this issue, we construct a \textbf{dual relation graph} where each node denotes a relation in the original KG (\textbf{primal entity graph}) and edges are constructed between relations sharing same head or tail entities.
MC^2: A Multilingual Corpus of Minority Languages in China
However, existing LLMs exhibit limited abilities in understanding low-resource languages, including the minority languages in China, due to a lack of training data.
From Simple to Complex: A Progressive Framework for Document-level Informative Argument Extraction
These methods extract events according to their appearance order in the document, however, the event that appears in the first sentence does not mean that it is the easiest to extract.
Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Specifically, we introduce a well-designed visual tokenizer to translate the non-linguistic image into a sequence of discrete tokens like a foreign language that LLM can read.
More than Classification: A Unified Framework for Event Temporal Relation Extraction
After examining the relation definitions in various ETRE tasks, we observe that all relations can be interpreted using the start and end time points of events.
Lawyer LLaMA Technical Report
Specifically, we inject domain knowledge during the continual training stage and teach the model to learn professional skills using properly designed supervised fine-tuning tasks.
Do Charge Prediction Models Learn Legal Theory?
The charge prediction task aims to predict the charge for a case given its fact description.
Knowledge-enhanced Iterative Instruction Generation and Reasoning for Knowledge Base Question Answering
Multi-hop Knowledge Base Question Answering(KBQA) aims to find the answer entity in a knowledge base which is several hops from the topic entity mentioned in the question.
Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocRED
DocRED is a widely used dataset for document-level relation extraction.
Exploring Distantly-Labeled Rationales in Neural Network Models
Recent studies strive to incorporate various human rationales into neural networks to improve model performance, but few pay attention to the quality of the rationales.
Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction
Document-level Relation Extraction (RE) is a more challenging task than sentence RE as it often requires reasoning over multiple sentences.
Ranked #48 on
Relation Extraction
on DocRED
Why Machine Reading Comprehension Models Learn Shortcuts?
A thorough empirical analysis shows that MRC models tend to learn shortcut questions earlier than challenging questions, and the high proportions of shortcut questions in training sets hinder models from exploring the sophisticated reasoning skills in the later stage of training.
Towards Context-Aware Code Comment Generation
Code comments are vital for software maintenance and comprehension, but many software projects suffer from the lack of meaningful and up-to-date comments in practice.
