MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control

Zhoues/MineDreamer 18 Mar 2024

It is a long-lasting goal to design a generalist-embodied agent that can follow diverse instructions in human-like ways.

10
18 Mar 2024

Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach

beichenzbc/supernet-shifting 18 Mar 2024

In this work, we analyze the order-preserving ability on the whole search space (global) and a sub-space of top architectures (local), and empirically show that the local order-preserving for current two-stage NAS methods still need to be improved.

1
18 Mar 2024

State-Separated SARSA: A Practical Sequential Decision-Making Algorithm with Recovering Rewards

yutanimoto/ss-sarsa 18 Mar 2024

While many multi-armed bandit algorithms assume that rewards for all arms are constant across rounds, this assumption does not hold in many real-world scenarios.

0
18 Mar 2024

VmambaIR: Visual State Space Model for Image Restoration

alphacatplus/vmambair 18 Mar 2024

To address these challenges, we propose VmambaIR, which introduces State Space Models (SSMs) with linear complexity into comprehensive image restoration tasks.

9
18 Mar 2024

EchoReel: Enhancing Action Generation of Existing Video Diffusion Models

liujianzhi/echoreel 18 Mar 2024

Recent large-scale video datasets have facilitated the generation of diverse open-domain videos of Video Diffusion Models (VDMs).

6
18 Mar 2024

Distilling Datasets Into Less Than One Image

AsafShul/PoDD 18 Mar 2024

Current methods frame this as maximizing the distilled classification accuracy for a budget of K distilled images-per-class, where K is a positive integer.

10
18 Mar 2024

LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models

young98cn/lora_composer 18 Mar 2024

Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts.

2
18 Mar 2024

Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models

gladia-research-group/gmsdi 18 Mar 2024

Multi-Source Diffusion Models (MSDM) allow for compositional musical generation tasks: generating a set of coherent sources, creating accompaniments, and performing source separation.

0
18 Mar 2024

HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation

zhangce01/HiKER-SGG 18 Mar 2024

Being able to understand visual scenes is a precursor for many downstream tasks, including autonomous driving, robotics, and other vision-based approaches.

8
18 Mar 2024

Circle Representation for Medical Instance Object Segmentation

hrlblab/circlesnake 18 Mar 2024

Recently, circle representation has been introduced for medical imaging, designed specifically to enhance the detection of instance objects that are spherically shaped (e. g., cells, glomeruli, and nuclei).

9
18 Mar 2024