Trending Research
BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
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.
Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance
KU-CVLAB/Perturbed-Attention-Guidance
•
•
These techniques are often not applicable in unconditional generation or in various downstream tasks such as image restoration.
PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language Models
3DAgentWorld/Toolkit-for-Prompt-Compression
•
•
Prompt compression is an innovative method for efficiently condensing input prompts while preserving essential information.
TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods
Next, we employ TFB to perform a thorough evaluation of 21 Univariate Time Series Forecasting (UTSF) methods on 8, 068 univariate time series and 14 Multivariate Time Series Forecasting (MTSF) methods on 25 datasets.
SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing
modelscope/swift
•
•
Image diffusion models have been utilized in various tasks, such as text-to-image generation and controllable image synthesis.
QLoRA: Efficient Finetuning of Quantized LLMs
internlm/xtuner
•
•
NeurIPS 2023
Our best model family, which we name Guanaco, outperforms all previous openly released models on the Vicuna benchmark, reaching 99. 3% of the performance level of ChatGPT while only requiring 24 hours of finetuning on a single GPU.
DUSt3R: Geometric 3D Vision Made Easy
naver/dust3r
•
•
Our formulation directly provides a 3D model of the scene as well as depth information, but interestingly, we can seamlessly recover from it, pixel matches, relative and absolute camera.
JetMoE: Reaching Llama2 Performance with 0.1M Dollars
Large Language Models (LLMs) have achieved remarkable results, but their increasing resource demand has become a major obstacle to the development of powerful and accessible super-human intelligence.
ObjectLab: Automated Diagnosis of Mislabeled Images in Object Detection Data
Despite powering sensitive systems like autonomous vehicles, object detection remains fairly brittle in part due to annotation errors that plague most real-world training datasets.
ReFT: Representation Finetuning for Language Models
LoReFT is a drop-in replacement for existing PEFTs and learns interventions that are 10x-50x more parameter-efficient than prior state-of-the-art PEFTs.
