Language Models are Few-Shot Learners

EleutherAI/lm_evaluation_harness NeurIPS 2020

By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do.

 Ranked #1 on Question Answering on CoQA (Overall metric)

Common Sense Reasoning Coreference Resolution +12

4,602
0.23 stars / hour

UniTS: Building a Unified Time Series Model

mims-harvard/UniTS 29 Feb 2024

However, current foundation models apply to sequence data but not to time series, which present unique challenges due to the inherent diverse and multidomain time series datasets, diverging task specifications across forecasting, classification and other types of tasks, and the apparent need for task-specialized models.

Anomaly Detection Imputation +1

234
0.22 stars / hour

HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression

yihangchen-ee/hac 21 Mar 2024

3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity.

Attribute Novel View Synthesis +1

60
0.22 stars / hour

Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting

KU-CVLAB/RAIN-GS 14 Mar 2024

Through extensive analysis of SfM initialization in the frequency domain and analysis of a 1D regression task with multiple 1D Gaussians, we propose a novel optimization strategy dubbed RAIN-GS (Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting), that successfully trains 3D Gaussians from random point clouds.

3D Reconstruction Novel View Synthesis

199
0.22 stars / hour

GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer

urchade/gliner 14 Nov 2023

Named Entity Recognition (NER) is essential in various Natural Language Processing (NLP) applications.

named-entity-recognition Named Entity Recognition +1

352
0.22 stars / hour

The Unreasonable Effectiveness of Eccentric Automatic Prompts

stanfordnlp/dspy 9 Feb 2024

Given the combinatorial complexity, and thus computation time, of experimenting with hand-tuning prompts for large black-box models, we then compared the performance of the best "positive thinking" prompt against the output of systematic prompt optimization.

Arithmetic Reasoning GSM8K

8,887
0.22 stars / hour

DUSt3R: Geometric 3D Vision Made Easy

naver/dust3r 21 Dec 2023

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.

3D Reconstruction Camera Calibration +2

3,630
0.22 stars / hour

SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing

modelscope/swift 18 Dec 2023

Image diffusion models have been utilized in various tasks, such as text-to-image generation and controllable image synthesis.

Text-to-Image Generation

909
0.22 stars / hour

DragAnything: Motion Control for Anything using Entity Representation

showlab/draganything 12 Mar 2024

We introduce DragAnything, which utilizes a entity representation to achieve motion control for any object in controllable video generation.

Object Video Generation

249
0.22 stars / hour

Online Vectorized HD Map Construction using Geometry

cnzzx/gemap 6 Dec 2023

In our work, we propose GeMap ($\textbf{Ge}$ometry $\textbf{Map}$), which end-to-end learns Euclidean shapes and relations of map instances beyond basic perception.

132
0.22 stars / hour