@@ -7,6 +7,14 @@ panel_includes:
7
7
- toc
8
8
---
9
9
10
+ #### JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse
11
+ [ Muyao Li* ] ( https://muyaoli-jimo.github.io ) , [ Zihao Wang* ] ( https://zhwang4ai.github.io/ ) , [ Kaichen He] ( https://zhwang4ai.github.io/ ) , [ Xiaojian Ma] ( https://jeasinema.github.io ) , [ Yitao Liang] ( https://scholar.google.com/citations?user=KVzR1XEAAAAJ&hl=en ) \
12
+ ** ACL 2025** [[ Project]] ( https://craftjarvis.github.io/JarvisVLA/ ) [[ Paper]] ( https://craftjarvis.github.io/JarvisVLA/files/JARVIS_VLA_paper.pdf ) [[ Code]] ( https://github.com/CraftJarvis/JarvisVLA )
13
+
14
+ #### MCU: A Task-centric Framework for Open-ended Agent Evaluation in Minecraft
15
+ [ Xinyue Zheng* ] ( https://craftjarvis.github.io/MCU/ ) , [ Haowei Lin* ] ( https://linhaowei1.github.io/ ) , [ Kaichen He] ( https://craftjarvis.github.io/MCU/ ) , [ Zihao Wang] ( https://zhwang4ai.github.io/ ) , [ Zilong Zheng] ( https://craftjarvis.github.io/MCU/ ) , [ Yitao Liang] ( https://web.cs.ucla.edu/~yliang/ ) \
16
+ ** ICML 2025 (Spotlight)** [[ Project]] ( https://craftjarvis.github.io/MCU/ ) [[ Paper]] ( https://arxiv.org/pdf/2310.08367.pdf ) [[ Code]] ( https://github.com/CraftJarvis/MCU )
17
+
10
18
#### ROCKET-1: Master Open-World Interaction with Visual-Temporal Context Prompting
11
19
[ Shaofei Cai] ( https://phython96.github.io/ ) , [ Zihao Wang] ( https://zhwang4ai.github.io/ ) , Kewei Lian, [ Zhancun Mu] ( https://zhancunmu.owlstown.net/ ) , [ Xiaojian Ma] ( https://web.cs.ucla.edu/~xm/ ) , [ Anji Liu] ( https://liuanji.github.io/ ) , [ Yitao Liang] ( https://web.cs.ucla.edu/~yliang/ ) \
12
20
** arXiv** [[ Project]] ( https://craftjarvis.github.io/ROCKET-1/ ) [[ Paper]] ( https://arxiv.org/pdf/2410.17856 ) [[ Code]] ( https://github.com/CraftJarvis/ROCKET-1 )
@@ -27,10 +35,6 @@ panel_includes:
27
35
[ Shaofei Cai] ( https://phython96.github.io/ ) , Bowei Zhang, [ Zihao Wang] ( https://zhwang4ai.github.io/ ) , [ Xiaojian Ma] ( https://web.cs.ucla.edu/~xm/ ) , [ Anji Liu] ( https://web.cs.ucla.edu/~yliang/ ) , [ Yitao Liang] ( https://web.cs.ucla.edu/~yliang/ ) \
28
36
** ICLR 2024 (Spotlight)** [[ Project]] ( https://craftjarvis.github.io/GROOT/ ) [[ Paper]] ( https://arxiv.org/pdf/2310.08235.pdf ) [[ Code]] ( https://github.com/CraftJarvis/GROOT ) [[ Twitter]] ( https://twitter.com/jeasinema/status/1712526192665047493 ) [[ Media]] ( https://mp.weixin.qq.com/s/IqIRxFYDpCi3_Iy1FUg9DQ )
29
37
30
- #### MCU: A Task-centric Framework for Open-ended Agent Evaluation in Minecraft
31
- [ Haowei Lin] ( https://linhaowei1.github.io/ ) , [ Zihao Wang] ( https://zhwang4ai.github.io/ ) , [ Jianzhu Ma] ( https://majianzhu.com/ ) , [ Yitao Liang] ( https://web.cs.ucla.edu/~yliang/ ) \
32
- ** arXiv** [[ Paper]] ( https://arxiv.org/pdf/2310.08367.pdf ) [[ Code]] ( https://github.com/CraftJarvis/MCU ) [[ Benchmark]] ( https://github.com/CraftJarvis/MC-TextWorld )
33
-
34
38
#### Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction
35
39
Shaofei Cai, Zihao Wang, Xiaojian Ma, Anji Liu, Yitao Liang\
36
40
** CVPR 2023** [[ Paper]] ( https://arxiv.org/pdf/2301.10034.pdf ) [[ Code]] ( https://github.com/CraftJarvis/MC-Controller )
0 commit comments