Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement

LingmaTongyi/Lingma-SWE-GPT 1 Nov 2024

The results demonstrate that Lingma SWE-GPT 72B successfully resolves 30. 20% of the GitHub issues, marking a significant improvement in automatic issue resolution (22. 76% relative improvement compared to Llama 3. 1 405B), approaching the performance of closed-source models (31. 80\% issues of GPT-4o resolved).

Language Modelling

114
0.78 stars / hour

Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodings

autodeskailab/wala 12 Nov 2024

We attribute this limitation to the inefficiency of current representations, which lack the compactness required to model the generative models effectively.

Attribute Computational Efficiency

23
0.75 stars / hour

LightRAG: Simple and Fast Retrieval-Augmented Generation

hkuds/lightrag 8 Oct 2024

Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user needs.

Information Retrieval RAG +1

8,272
0.74 stars / hour

ADOPT: Modified Adam Can Converge with Any $β_2$ with the Optimal Rate

ishohei220/adopt 5 Nov 2024

Adam is one of the most popular optimization algorithms in deep learning.

Image Classification

266
0.67 stars / hour

TableGPT2: A Large Multimodal Model with Tabular Data Integration

tablegpt/tablegpt-agent 4 Nov 2024

In response, we introduce TableGPT2, a model rigorously pre-trained and fine-tuned with over 593. 8K tables and 2. 36M high-quality query-table-output tuples, a scale of table-related data unprecedented in prior research.

Benchmarking Data Integration

221
0.66 stars / hour

Taming Rectified Flow for Inversion and Editing

wangjiangshan0725/rf-solver-edit 7 Nov 2024

Rectified-flow-based diffusion transformers, such as FLUX and OpenSora, have demonstrated exceptional performance in the field of image and video generation.

Text-to-Image Generation Video Editing +1

123
0.65 stars / hour

LLM2CLIP: Powerful Language Model Unlock Richer Visual Representation

microsoft/LLM2CLIP 7 Nov 2024

In this paper, we propose LLM2CLIP, a novel approach that embraces the power of LLMs to unlock CLIP's potential.

Contrastive Learning Image Captioning +3

86
0.64 stars / hour

TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control

AaronZ345/TCSinger 24 Sep 2024

To address these challenges, we introduce TCSinger, the first zero-shot SVS model for style transfer across cross-lingual speech and singing styles, along with multi-level style control.

Clustering Language Modelling +3

106
0.63 stars / hour

optillm

codelion/optillm 25 Jun 2024

Optimizing inference proxy for LLMs

Open-Domain Question Answering Retrieval

1,483
0.62 stars / hour

TransformerRanker: A Tool for Efficiently Finding the Best-Suited Language Models for Downstream Classification Tasks

flairnlp/transformer-ranker 9 Sep 2024

Classification tasks in NLP are typically addressed by selecting a pre-trained language model (PLM) from a model hub, and fine-tuning it for the task at hand.

Classification Language Modelling

78
0.60 stars / hour