Angle-optimized text embeddings

X Li, J Li - arxiv preprint arxiv:2309.12871, 2023 - arxiv.org
High-quality text embedding is pivotal in improving semantic textual similarity (STS) tasks,
which are crucial components in Large Language Model (LLM) applications. However, a …

Animatabledreamer: Text-guided non-rigid 3d model generation and reconstruction with canonical score distillation

X Wang, Y Wang, J Ye, F Sun, Z Wang, L Wang… - … on Computer Vision, 2024 - Springer
Advances in 3D generation have facilitated sequential 3D model generation (aka 4D
generation), yet its application for animatable objects with large motion remains scarce. Our …

AoE: Angle-optimized embeddings for semantic textual similarity

X Li, J Li - Proceedings of the 62nd Annual Meeting of the …, 2024 - aclanthology.org
Text embedding is pivotal in semantic textual similarity (STS) tasks, which are crucial
components in Large Language Model (LLM) applications. STS learning largely relies on …

Vividdreamer: invariant score distillation for hyper-realistic text-to-3d generation

W Zhuo, F Ma, H Fan, Y Yang - European Conference on Computer Vision, 2024 - Springer
Abstract This paper presents Invariant Score Distillation (ISD), a novel method for high-
fidelity text-to-3D generation. ISD aims to tackle the over-saturation and over-smoothing …

Mind-3D: reconstruct high-quality 3D objects in human brain

J Gao, Y Fu, Y Wang, X Qian, J Feng, Y Fu - European Conference on …, 2024 - Springer
In this paper, we introduce Recon3DMind, an innovative task aimed at reconstructing 3D
visuals from Functional Magnetic Resonance Imaging (fMRI) signals, marking a significant …

Automatic smart contract comment generation via large language models and in-context learning

J Zhao, X Chen, G Yang, Y Shen - Information and Software Technology, 2024 - Elsevier
Context: Designing effective automatic smart contract comment generation approaches can
facilitate developers' comprehension, boosting smart contract development and improving …

2d matryoshka sentence embeddings

X Li, Z Li, J Li, H **e, Q Li - arxiv preprint arxiv:2402.14776, 2024 - arxiv.org
Common approaches rely on fixed-length embedding vectors from language models as
sentence embeddings for downstream tasks such as semantic textual similarity (STS). Such …

DeeLM: Dependency-enhanced Large Language Model for Sentence Embeddings

X Li, J Li - arxiv preprint arxiv:2311.05296, 2023 - arxiv.org
Recent studies have proposed using large language models (LLMs) for sentence
embeddings. However, most existing LLMs are built with an autoregressive architecture that …

When Text Embedding Meets Large Language Model: A Comprehensive Survey

Z Nie, Z Feng, M Li, C Zhang, Y Zhang, D Long… - arxiv preprint arxiv …, 2024 - arxiv.org
Text embedding has become a foundational technology in natural language processing
(NLP) during the deep learning era, driving advancements across a wide array of …

BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings

X Li, J Li - Proceedings of the 2024 Conference of the North …, 2024 - aclanthology.org
Sentence embeddings are crucial in measuring semantic similarity. Most recent studies
employed large language models (LLMs) to learn sentence embeddings. Existing LLMs …