Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework

ictmcg/make-your-anchor 25 Mar 2024

We adopt a two-stage training strategy for the diffusion model, effectively binding movements with specific appearances.

Denoising

135
1.67 stars / hour

FeatUp: A Model-Agnostic Framework for Features at Any Resolution

mhamilton723/FeatUp 15 Mar 2024

Deep features are a cornerstone of computer vision research, capturing image semantics and enabling the community to solve downstream tasks even in the zero- or few-shot regime.

Depth Estimation Depth Prediction +5

862
1.47 stars / hour

Analyzing and Improving the Training Dynamics of Diffusion Models

nvlabs/edm2 5 Dec 2023

Diffusion models currently dominate the field of data-driven image synthesis with their unparalleled scaling to large datasets.

Image Generation Philosophy

239
1.39 stars / hour

Long-CLIP: Unlocking the Long-Text Capability of CLIP

beichenzbc/long-clip 22 Mar 2024

Contrastive Language-Image Pre-training (CLIP) has been the cornerstone for zero-shot classification, text-image retrieval, and text-image generation by aligning image and text modalities.

Image Retrieval Language Modelling +3

161
1.33 stars / hour

One-Step Image Translation with Text-to-Image Models

gaparmar/img2img-turbo 18 Mar 2024

In this work, we address two limitations of existing conditional diffusion models: their slow inference speed due to the iterative denoising process and their reliance on paired data for model fine-tuning.

Denoising Translation

773
1.30 stars / hour

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

microsoft/LLMLingua 19 Mar 2024

The challenge is that information entropy may be a suboptimal compression metric: (i) it only leverages unidirectional context and may fail to capture all essential information needed for prompt compression; (ii) it is not aligned with the prompt compression objective.

GSM8K Language Modelling +3

3,404
1.10 stars / hour

A Survey of Neural Code Intelligence: Paradigms, Advances and Beyond

qiushisun/ncisurvey 21 Mar 2024

Building on our examination of the developmental trajectories, we further investigate the emerging synergies between code intelligence and broader machine intelligence, uncovering new cross-domain opportunities and illustrating the substantial influence of code intelligence across various domains.

106
0.82 stars / hour

LLM4Decompile: Decompiling Binary Code with Large Language Models

albertan017/LLM4Decompile 8 Mar 2024

Therefore, we release the first open-access decompilation LLMs ranging from 1B to 33B pre-trained on 4 billion tokens of C source code and the corresponding assembly code.

2,147
0.76 stars / hour

Long-form factuality in large language models

google-deepmind/long-form-factuality 27 Mar 2024

Empirically, we demonstrate that LLM agents can achieve superhuman rating performance - on a set of ~16k individual facts, SAFE agrees with crowdsourced human annotators 72% of the time, and on a random subset of 100 disagreement cases, SAFE wins 76% of the time.

143
0.75 stars / hour

MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

donydchen/mvsplat 21 Mar 2024

We propose MVSplat, an efficient feed-forward 3D Gaussian Splatting model learned from sparse multi-view images.

3D Reconstruction Generalizable Novel View Synthesis +2

270
0.74 stars / hour