BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation

flagopen/flagembedding 5 Feb 2024

It can simultaneously perform the three common retrieval functionalities of embedding model: dense retrieval, multi-vector retrieval, and sparse retrieval, which provides a unified model foundation for real-world IR applications.

Retrieval Self-Knowledge Distillation

4,319
0.42 stars / hour

Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation

shihaozhaozsh/lavi-bridge 12 Mar 2024

In this paper, we explore this objective and propose LaVi-Bridge, a pipeline that enables the integration of diverse pre-trained language models and generative vision models for text-to-image generation.

Language Modelling Text-to-Image Generation

200
0.42 stars / hour

OMG-Seg: Is One Model Good Enough For All Segmentation?

lxtgh/omg-seg 18 Jan 2024

In this work, we address various segmentation tasks, each traditionally tackled by distinct or partially unified models.

Interactive Segmentation Panoptic Segmentation +3

664
0.41 stars / hour

Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy

zshsh98/mmd-mp 25 Feb 2024

Unfortunately, it is challenging to distinguish MGTs and human-written texts because the distributional discrepancy between them is often very subtle due to the remarkable performance of LLMs.

Hallucination Sentence

35
0.41 stars / hour

DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

Doubiiu/DynamiCrafter 18 Oct 2023

Animating a still image offers an engaging visual experience.

Image Animation

1,401
0.41 stars / hour

Aggregated Contextual Transformations for High-Resolution Image Inpainting

zyddnys/manga-image-translator 3 Apr 2021

For improving texture synthesis, we enhance the discriminator of AOT-GAN by training it with a tailored mask-prediction task.

Image Inpainting Texture Synthesis +1

3,984
0.40 stars / hour

Logit Standardization in Knowledge Distillation

sunshangquan/logit-standardardization-kd 3 Mar 2024

Knowledge distillation involves transferring soft labels from a teacher to a student using a shared temperature-based softmax function.

Knowledge Distillation

74
0.39 stars / hour

Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling

kuleshov-group/caduceus 5 Mar 2024

Large-scale sequence modeling has sparked rapid advances that now extend into biology and genomics.

83
0.38 stars / hour

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

yl4579/StyleTTS2 NeurIPS 2023

In this paper, we present StyleTTS 2, a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis.

Speech Synthesis

3,853
0.37 stars / hour

Leveraging Enhanced Queries of Point Sets for Vectorized Map Construction

hxmap/mapqr 27 Feb 2024

Although the map construction is essentially a point set prediction task, MapQR utilizes instance queries rather than point queries.

Autonomous Driving

77
0.37 stars / hour