Skip to content

Commit be463a5

Browse files
Guanya ShiGuanya Shi
Guanya Shi
authored and
Guanya Shi
committed
papers
1 parent c72ae12 commit be463a5

4 files changed

Lines changed: 73 additions & 25 deletions

File tree

‎index.html‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -109,6 +109,7 @@
109109
<tr>
110110
<td width="100%" valign="middle">
111111
<ul>
112+
<li>2026-03-01: <a href="https://viral-humanoid.github.io/" target="_blank">VIRAL</a> and <a href="https://doorman-humanoid.github.io/" target="_blank">DoorMan</a> accepted to CVPR 2026.</li>
112113
<li>2026-01-31: Four papers accepted to ICLR 2026, two to L4DC 2026, and six to ICRA 2026.</li>
113114
<li>2025-10-21: Congratulations to Zeji for receiving the <a href="https://www.cs.cmu.edu/news/2025/amazon-phd-fellows" target="_blank">Amazon AI Ph.D. Fellowship</a>, and Wenli for receiving the CMU RI Presidential Fellowship!</li>
114115
<li>2025-08-01: <a href="https://lecar-lab.github.io/spi-active_/" target="_blank">SPI-Active</a> (oral), <a href="https://lecar-lab.github.io/SoFTA/" target="_blank">HoldMyBeer</a>, and <a href="https://human-as-robot.github.io/" target="_blank">Humanoid~Human</a> accepted to CoRL 2025.</li>

‎publications.html‎

Lines changed: 72 additions & 25 deletions
Original file line numberDiff line numberDiff line change
@@ -78,17 +78,17 @@
7878
<tr>
7979
<td style="width:35%; vertical-align:middle; padding-right: 20px;">
8080
<div class="image-container">
81-
<img src='publications/2026_RPL.gif' width="100%">
81+
<img src='publications/2026_PHP.gif' width="100%">
8282
</div>
8383
</td>
8484
<td style="width:65%; vertical-align:middle">
85-
<papertitle>RPL: Learning Robust Humanoid Perceptive Locomotion on Challenging Terrains</papertitle>
85+
<papertitle>Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching</papertitle>
8686
<br>
87-
Yuanhang Zhang, Younggyo Seo, Juyue Chen, Yifu Yuan, Koushil Sreenath, Pieter Abbeel<sup>&dagger;</sup>, Carmelo Sferrazza<sup>&dagger;</sup>, Karen Liu<sup>&dagger;</sup>, Rocky Duan<sup>&dagger;</sup>, Guanya Shi<sup>&dagger;</sup>
87+
Zhen Wu<sup>*</sup>, Xiaoyu Huang<sup>*</sup>, Lujie Yang<sup>*</sup>, Yuanhang Zhang, Koushil Sreenath, Xi Chen, Pieter Abbeel<sup>&dagger;</sup>, Rocky Duan<sup>&dagger;</sup>, Angjoo Kanazawa<sup>&dagger;</sup>, Carmelo Sferrazza<sup>&dagger;</sup>, Guanya Shi<sup>&dagger;</sup>, C. Karen Liu<sup>&dagger;</sup>
8888
<br>
89-
<a href="https://arxiv.org/abs/2602.03002" target="_blank"><i class="far fa-file"></i> paper</a> &nbsp
90-
<a href="https://rpl-humanoid.github.io/" target="_blank"><i class="fas fa-globe"></i> website</a>
91-
<p style="margin-top: 5px"><i class="fas fa-comment-dots"></i> TL;DR: A single policy trained by RPL enables multi-directional robust humanoid locomotion over various challenging terrains.
89+
<a href="https://arxiv.org/abs/2602.15827" target="_blank"><i class="far fa-file"></i> paper</a> &nbsp
90+
<a href="https://php-parkour.github.io/" target="_blank"><i class="fas fa-globe"></i> website</a>
91+
<p style="margin-top: 5px"><i class="fas fa-comment-dots"></i> TL;DR: PHP enables humanoid robots to autonomously perform long-horizon, vision-based parkour across challenging obstacle courses.
9292
</td>
9393
</tr>
9494
</table>
@@ -99,18 +99,18 @@
9999
<tr>
100100
<td style="width:35%; vertical-align:middle; padding-right: 20px;">
101101
<div class="image-container">
102-
<img src='publications/2025_FastSAC.gif' width="100%">
102+
<img src='publications/2026_FPO.gif' width="100%">
103103
</div>
104104
</td>
105105
<td style="width:65%; vertical-align:middle">
106-
<papertitle>Learning Sim-to-Real Humanoid Locomotion in 15 Minutes</papertitle>
106+
<papertitle>Flow Policy Gradients for Robot Control</papertitle>
107107
<br>
108-
Younggyo Seo, Carmelo Sferrazza, Juyue Chen, Guanya Shi, Rocky Duan, Pieter Abbeel
108+
Brent Yi<sup>*</sup>, Hongsuk Choi<sup>*</sup>, Himanshu Gaurav Singh, Xiaoyu Huang, Takara E. Truong, Carmelo Sferrazza, Yi Ma, Rocky Duan<sup>&dagger;</sup>, Pieter Abbeel<sup>&dagger;</sup>, Guanya Shi<sup>&dagger;</sup>, Karen Liu<sup>&dagger;</sup>, Angjoo Kanazawa<sup>&dagger;</sup>
109109
<br>
110-
<a href="https://arxiv.org/abs/2512.01996" target="_blank"><i class="far fa-file"></i> paper</a> &nbsp
111-
<a href="https://younggyo.me/fastsac-humanoid/" target="_blank"><i class="fas fa-globe"></i> website</a> &nbsp
112-
<a href="https://github.com/amazon-far/holosoma" target="_blank"><i class="fas fa-code"></i> code</a>
113-
<p style="margin-top: 5px"><i class="fas fa-comment-dots"></i> TL;DR: We provide a simple recipe with FastSAC and FastTD3 for rapid sim2real humanoid learning.
110+
<a href="https://arxiv.org/abs/2602.02481" target="_blank"><i class="far fa-file"></i> paper</a> &nbsp
111+
<a href="https://hongsukchoi.github.io/fpo-control/" target="_blank"><i class="fas fa-globe"></i> website</a> &nbsp
112+
<a href="https://github.com/amazon-far/fpo-control" target="_blank"><i class="fas fa-code"></i> code</a>
113+
<p style="margin-top: 5px"><i class="fas fa-comment-dots"></i> TL;DR: A simple recipe for online RL with flow policies, validated in robot locomotion, humanoid motion tracking, and manipulation.
114114
</td>
115115
</tr>
116116
</table>
@@ -121,17 +121,17 @@
121121
<tr>
122122
<td style="width:35%; vertical-align:middle; padding-right: 20px;">
123123
<div class="image-container">
124-
<img src='publications/2025_DoorMan.gif' width="90%">
124+
<img src='publications/2026_RPL.gif' width="100%">
125125
</div>
126126
</td>
127127
<td style="width:65%; vertical-align:middle">
128-
<papertitle>Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer</papertitle>
128+
<papertitle>RPL: Learning Robust Humanoid Perceptive Locomotion on Challenging Terrains</papertitle>
129129
<br>
130-
Haoru Xue<sup>*</sup>, Tairan He<sup>*</sup>, Zi Wang<sup>*</sup>, Qingwei Ben, Wenli Xiao, Zhengyi Luo, Xingye Da, Fernando Castañeda, Guanya Shi, Shankar Sastry, Linxi "Jim" Fan, Yuke Zhu
130+
Yuanhang Zhang, Younggyo Seo, Juyue Chen, Yifu Yuan, Koushil Sreenath, Pieter Abbeel<sup>&dagger;</sup>, Carmelo Sferrazza<sup>&dagger;</sup>, Karen Liu<sup>&dagger;</sup>, Rocky Duan<sup>&dagger;</sup>, Guanya Shi<sup>&dagger;</sup>
131131
<br>
132-
<a href="https://arxiv.org/abs/2512.01061" target="_blank"><i class="far fa-file"></i> paper</a> &nbsp
133-
<a href="https://doorman-humanoid.github.io/" target="_blank"><i class="fas fa-globe"></i> website</a>
134-
<p style="margin-top: 5px"><i class="fas fa-comment-dots"></i> TL;DR: DoorMan proposes a teacher-student-bootstrap framework for challenging humanoid loco-manipulation tasks such as door opening.
132+
<a href="https://arxiv.org/abs/2602.03002" target="_blank"><i class="far fa-file"></i> paper</a> &nbsp
133+
<a href="https://rpl-humanoid.github.io/" target="_blank"><i class="fas fa-globe"></i> website</a>
134+
<p style="margin-top: 5px"><i class="fas fa-comment-dots"></i> TL;DR: A single policy trained by RPL enables multi-directional robust humanoid locomotion over various challenging terrains.
135135
</td>
136136
</tr>
137137
</table>
@@ -142,17 +142,18 @@
142142
<tr>
143143
<td style="width:35%; vertical-align:middle; padding-right: 20px;">
144144
<div class="image-container">
145-
<img src='publications/2025_VIRAL.gif' width="90%">
145+
<img src='publications/2025_FastSAC.gif' width="100%">
146146
</div>
147147
</td>
148148
<td style="width:65%; vertical-align:middle">
149-
<papertitle>VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation</papertitle>
149+
<papertitle>Learning Sim-to-Real Humanoid Locomotion in 15 Minutes</papertitle>
150150
<br>
151-
Tairan He<sup>*</sup>, Zi Wang<sup>*</sup>, Haoru Xue<sup>*</sup>, Qingwei Ben<sup>*</sup>, Zhengyi Luo, Wenli Xiao, Ye Yuan, Xingye Da, Fernando Castañeda, Shankar Sastry, Changliu Liu, Guanya Shi, Linxi Fan, Yuke Zhu
151+
Younggyo Seo<sup>*</sup>, Carmelo Sferrazza<sup>*</sup>, Juyue Chen, Guanya Shi, Rocky Duan, Pieter Abbeel
152152
<br>
153-
<a href="https://arxiv.org/abs/2511.15200" target="_blank"><i class="far fa-file"></i> paper</a> &nbsp
154-
<a href="https://viral-humanoid.github.io/" target="_blank"><i class="fas fa-globe"></i> website</a>
155-
<p style="margin-top: 5px"><i class="fas fa-comment-dots"></i> TL;DR: VIRAL investigates the scaling law of visual sim-to-real and finds a recipe to achieve zero-shot, robust, and continuous real-world deployment.
153+
<a href="https://arxiv.org/abs/2512.01996" target="_blank"><i class="far fa-file"></i> paper</a> &nbsp
154+
<a href="https://younggyo.me/fastsac-humanoid/" target="_blank"><i class="fas fa-globe"></i> website</a> &nbsp
155+
<a href="https://github.com/amazon-far/holosoma" target="_blank"><i class="fas fa-code"></i> code</a>
156+
<p style="margin-top: 5px"><i class="fas fa-comment-dots"></i> TL;DR: We provide a simple recipe with FastSAC and FastTD3 for rapid sim2real humanoid learning.
156157
</td>
157158
</tr>
158159
</table>
@@ -255,6 +256,52 @@
255256
</tr>
256257
</table>
257258

259+
<table width="880" border="0" align="center" cellspacing="0" cellpadding="0">
260+
<tr>
261+
<td style="width:35%; vertical-align:middle; padding-right: 20px;">
262+
<div class="image-container">
263+
<img src='publications/2025_DoorMan.gif' width="90%">
264+
</div>
265+
</td>
266+
<td style="width:65%; vertical-align:middle">
267+
<papertitle>Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer</papertitle>
268+
<br>
269+
Haoru Xue<sup>*</sup>, Tairan He<sup>*</sup>, Zi Wang<sup>*</sup>, Qingwei Ben, Wenli Xiao, Zhengyi Luo, Xingye Da, Fernando Castañeda, Guanya Shi, Shankar Sastry, Linxi "Jim" Fan, Yuke Zhu
270+
<br>
271+
<em>IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR)</em>, 2026
272+
<br>
273+
<a href="https://arxiv.org/abs/2512.01061" target="_blank"><i class="far fa-file"></i> paper</a> &nbsp
274+
<a href="https://doorman-humanoid.github.io/" target="_blank"><i class="fas fa-globe"></i> website</a>
275+
<p style="margin-top: 5px"><i class="fas fa-comment-dots"></i> TL;DR: DoorMan proposes a teacher-student-bootstrap framework for challenging humanoid loco-manipulation tasks such as door opening.
276+
</td>
277+
</tr>
278+
</table>
279+
280+
<br>
281+
282+
<table width="880" border="0" align="center" cellspacing="0" cellpadding="0">
283+
<tr>
284+
<td style="width:35%; vertical-align:middle; padding-right: 20px;">
285+
<div class="image-container">
286+
<img src='publications/2025_VIRAL.gif' width="90%">
287+
</div>
288+
</td>
289+
<td style="width:65%; vertical-align:middle">
290+
<papertitle>VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation</papertitle>
291+
<br>
292+
Tairan He<sup>*</sup>, Zi Wang<sup>*</sup>, Haoru Xue<sup>*</sup>, Qingwei Ben<sup>*</sup>, Zhengyi Luo, Wenli Xiao, Ye Yuan, Xingye Da, Fernando Castañeda, Shankar Sastry, Changliu Liu, Guanya Shi, Linxi Fan, Yuke Zhu
293+
<br>
294+
<em>IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR)</em>, 2026
295+
<br>
296+
<a href="https://arxiv.org/abs/2511.15200" target="_blank"><i class="far fa-file"></i> paper</a> &nbsp
297+
<a href="https://viral-humanoid.github.io/" target="_blank"><i class="fas fa-globe"></i> website</a>
298+
<p style="margin-top: 5px"><i class="fas fa-comment-dots"></i> TL;DR: VIRAL investigates the scaling law of visual sim-to-real and finds a recipe to achieve zero-shot, robust, and continuous real-world deployment.
299+
</td>
300+
</tr>
301+
</table>
302+
303+
<br>
304+
258305
<table width="880" border="0" align="center" cellspacing="0" cellpadding="0">
259306
<tr style="background-color: var(--highlight-color)">
260307
<td style="width:35%; vertical-align:middle; padding-right: 20px;">

‎publications/2026_FPO.gif‎

2.87 MB
Loading

‎publications/2026_PHP.gif‎

5.02 MB
Loading

0 commit comments

Comments
 (0)