OmniFusion Technical Report

airi-institute/omnifusion 9 Apr 2024

We propose an \textit{OmniFusion} model based on a pretrained LLM and adapters for visual modality.

Visual Question Answering

134
1.59 stars / hour

Hash3D: Training-free Acceleration for 3D Generation

Adamdad/hash3D 9 Apr 2024

The evolution of 3D generative modeling has been notably propelled by the adoption of 2D diffusion models.

Image to 3D Text to 3D

75
0.99 stars / hour

Video-Based Human Pose Regression via Decoupled Space-Time Aggregation

zgspose/dsta 29 Mar 2024

In light of this, we propose a novel Decoupled Space-Time Aggregation network (DSTA) to separately capture the spatial contexts between adjacent joints and the temporal cues of each individual joint, thereby avoiding the conflation of spatiotemporal dimensions.

Pose Estimation regression

82
0.85 stars / hour

HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach

airi-institute/hairfastgan 1 Apr 2024

Our paper addresses the complex task of transferring a hairstyle from a reference image to an input photo for virtual hair try-on.

151
0.81 stars / hour

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

scutzzj/aniportrait 26 Mar 2024

In this study, we propose AniPortrait, a novel framework for generating high-quality animation driven by audio and a reference portrait image.

Face Reenactment

3,379
0.79 stars / hour

ReFT: Representation Finetuning for Language Models

stanfordnlp/pyreft 4 Apr 2024

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.

Arithmetic Reasoning

466
0.77 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

572
0.75 stars / hour

Policy-Guided Diffusion

emptyjackson/policy-guided-diffusion 9 Apr 2024

Our approach provides an effective alternative to autoregressive offline world models, opening the door to the controllable generation of synthetic training data.

43
0.74 stars / hour

Cross-Attention Makes Inference Cumbersome in Text-to-Image Diffusion Models

haozheliu-st/t-gate 3 Apr 2024

This study explores the role of cross-attention during inference in text-conditional diffusion models.

181
0.72 stars / hour

Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation

sail-sg/clot 5 Dec 2023

To this end, we study LLMs on the popular Oogiri game which needs participants to have good creativity and strong associative thinking for responding unexpectedly and humorously to the given image, text, or both, and thus is suitable for LoT study.

Logical Reasoning

173
0.71 stars / hour