From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples

robertvacareanu/llm4regression 11 Apr 2024

We analyze how well pre-trained large language models (e. g., Llama2, GPT-4, Claude 3, etc) can do linear and non-linear regression when given in-context examples, without any additional training or gradient updates.

Language Modelling Large Language Model +1

0.92 stars / hour

TinyLlama: An Open-Source Small Language Model

Lightning-AI/lit-gpt 4 Jan 2024

We present TinyLlama, a compact 1. 1B language model pretrained on around 1 trillion tokens for approximately 3 epochs.

Computational Efficiency Language Modelling

0.81 stars / hour

Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution

pku-yuangroup/open-sora-plan 12 Jul 2023

The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution before processing them with computer vision models has not yet been successfully challenged.

Fairness Image Classification +5

0.65 stars / hour

SchurVINS: Schur Complement-Based Lightweight Visual Inertial Navigation System

bytedance/schurvins 4 Dec 2023

To this end, we propose a novel filter-based VINS framework named SchurVINS, which could guarantee both high accuracy by building a complete residual model and low computational complexity with Schur complement.

Computational Efficiency

0.65 stars / hour

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

mcgill-nlp/llm2vec 9 Apr 2024

We outperform encoder-only models by a large margin on word-level tasks and reach a new unsupervised state-of-the-art performance on the Massive Text Embeddings Benchmark (MTEB).

Contrastive Learning

0.63 stars / hour

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

fudan-generative-vision/champ 21 Mar 2024

In this study, we introduce a methodology for human image animation by leveraging a 3D human parametric model within a latent diffusion framework to enhance shape alignment and motion guidance in curernt human generative techniques.

Animated GIF Generation Image Animation +1

0.62 stars / hour

StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text

picsart-ai-research/streamingt2v 21 Mar 2024

To overcome these limitations, we introduce StreamingT2V, an autoregressive approach for long video generation of 80, 240, 600, 1200 or more frames with smooth transitions.

Text-to-Video Generation Video Generation

0.61 stars / hour

GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo

wuuu3511/gomvs 11 Apr 2024

More specifically, we correspond and propagate adjacent costs to the reference pixel by leveraging the local geometric smoothness in conjunction with surface normals.

0.60 stars / hour

Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models

google-deepmind/recurrentgemma 29 Feb 2024

Recurrent neural networks (RNNs) have fast inference and scale efficiently on long sequences, but they are difficult to train and hard to scale.

Language Modelling

0.59 stars / hour

InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation

instantstyle/instantstyle 3 Apr 2024

Tuning-free diffusion-based models have demonstrated significant potential in the realm of image personalization and customization.

Text-to-Image Generation

0.53 stars / hour