Picture for Runhao Zeng

Runhao Zeng

Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layers

Add code
Dec 22, 2024
Viaarxiv icon

Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution

Add code
Dec 18, 2024
Viaarxiv icon

Towards Long Video Understanding via Fine-detailed Video Story Generation

Add code
Dec 09, 2024
Figure 1 for Towards Long Video Understanding via Fine-detailed Video Story Generation
Figure 2 for Towards Long Video Understanding via Fine-detailed Video Story Generation
Figure 3 for Towards Long Video Understanding via Fine-detailed Video Story Generation
Figure 4 for Towards Long Video Understanding via Fine-detailed Video Story Generation
Viaarxiv icon

Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning

Add code
Dec 07, 2024
Viaarxiv icon

Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions

Add code
Mar 29, 2024
Viaarxiv icon

DCIR: Dynamic Consistency Intrinsic Reward for Multi-Agent Reinforcement Learning

Add code
Dec 10, 2023
Viaarxiv icon

$A^2$Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models

Add code
Aug 15, 2023
Figure 1 for $A^2$Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models
Figure 2 for $A^2$Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models
Figure 3 for $A^2$Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models
Figure 4 for $A^2$Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models
Viaarxiv icon

Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation

Add code
Oct 14, 2022
Figure 1 for Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation
Figure 2 for Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation
Figure 3 for Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation
Figure 4 for Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation
Viaarxiv icon

Graph Convolutional Module for Temporal Action Localization in Videos

Add code
Dec 01, 2021
Figure 1 for Graph Convolutional Module for Temporal Action Localization in Videos
Figure 2 for Graph Convolutional Module for Temporal Action Localization in Videos
Figure 3 for Graph Convolutional Module for Temporal Action Localization in Videos
Figure 4 for Graph Convolutional Module for Temporal Action Localization in Videos
Viaarxiv icon

Location-aware Graph Convolutional Networks for Video Question Answering

Add code
Aug 07, 2020
Figure 1 for Location-aware Graph Convolutional Networks for Video Question Answering
Figure 2 for Location-aware Graph Convolutional Networks for Video Question Answering
Figure 3 for Location-aware Graph Convolutional Networks for Video Question Answering
Figure 4 for Location-aware Graph Convolutional Networks for Video Question Answering
Viaarxiv icon