Skip to content

Commit cda24fd

Browse files
francissfyfrancissfy
committed
update proj papers
1 parent e3718d9 commit cda24fd

4 files changed

Lines changed: 115 additions & 3 deletions

File tree

‎index.html‎

Lines changed: 115 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -44,6 +44,16 @@
4444
max-width: 100%;
4545
max-height: 100%;
4646
}
47+
.footnote_btn {
48+
display: inline-block;
49+
border: 1px solid black;
50+
padding: 4px 15px 4px 15px;
51+
border-radius: 3px;
52+
font-size: 8px;
53+
margin: 5px 10px 5px 0px;
54+
color: black;
55+
text-decoration: none;
56+
}
4757
</style>
4858
</head>
4959

@@ -64,13 +74,12 @@
6474
</div> -->
6575
<div class="container pt-5 mt-5 shadow-lg p-5 mb-5 bg-white rounded">
6676
<div class="text-center">
67-
<h1>FireRed Team （小红书智创音频团队）</h1>
77+
<h1>FireRed（by Xiaohongshu's Super Intelligence Team）</h1>
6878
</div>
6979
<div class="text-left">
7080
<br><br>
7181
<div><img src="pics/logo.png" alt="Left image" class="left"></div>
7282
<div>
73-
<!-- <b>Introduction: </b> FireRed is an innovative team within Xiaohongshu that specializes in speech, music, and text intelligence. Our mission is to provide users with more natural, fluent, and personalized voice interaction experiences through cutting-edge research and development. Whether in voice interaction, music generation, or text processing, we strive for excellence and aim to create the most advanced solutions in the industry. We will continue to push boundaries and provide users with smarter, more human-centered voice interaction experiences. -->
7483
<p><b>Introduction: </b> FireRed is the model series developed by Xiaohongshu's Super Intelligence team, featuring FireRed-ASR, FireRed-TTS, FireRed-Chat, FireRed-OCR, FireRed-Image, and FireRed-OpenStoryline.</p>
7584

7685
<p>Deriving from the saying "A single spark can start a prairie fire", the name FireRed represents our vision: to spread our SOTA capabilities—honed in real-world scenarios—like sparks across the wilderness, igniting the imagination of developers worldwide to reshape the future of AI together.</p>
@@ -79,12 +88,114 @@ <h1>FireRed Team （小红书智创音频团队）</h1>
7988

8089
<p>As the company's core technical engine for future content forms and General Intelligence, the team aims to build an industry-leading multimodal foundation model system with sustainable, evolving capabilities. We consistently benchmark industry SOTA across content understanding, vision and multimodal, image generation and editing, speech understanding and generation, Omni Models, and effect rendering, while prioritizing the scalability and practical deployment of these models in complex business scenarios. Responsible for core R&D in content creation and publishing, we empower business lines such as Recommendation, Search, Video & Live Streaming, E-commerce, Advertising, and International Growth, establishing cutting-edge technology as the foundation for long-term growth and innovation.</p>
8190

82-
<p>Over the past two years, we have excelled in both academia and industry, publishing over 30 top-tier papers and releasing influential open-source projects like InstantID, StoryMaker, FireRedTTS, and FireRedASR. On the product side, we successfully incubated hit features such as Audio Comments, Text Posters, Long Articles, and Full-Screen HD. We build frontier models while translating technology into impactful products. If you are passionate about general intelligence, cutting-edge models, and creating real-world impact, we welcome you to join us!</p>
91+
<p>Over the past two years, we have excelled in both academia and industry, publishing over 40 top-tier papers and releasing influential open-source projects like InstantID, StoryMaker, FireRedTTS, and FireRedASR. On the product side, we successfully incubated hit features such as Audio Comments（语音评论）, Text Posters（文生图大字报）, Long Articles（长文）, and Full-Screen HD（满屏高清）. We build frontier models while translating technology into impactful products. If you are passionate about general intelligence, cutting-edge models, and creating real-world impact, we welcome you to join us!</p>
8392
</div>
8493
</div>
8594

8695
</div>
8796

97+
98+
<div class="container pt-5 mt-5 shadow-lg p-5 mb-5 bg-white rounded">
99+
<h2 id="OpenSourceProjects" style="text-align: center;">Opensource Projects</h2>
100+
<table border="0" cellPadding="2" style="width: 100%;">
101+
<tbody>
102+
<!-- Data row 1 -->
103+
<tr>
104+
<!-- Image -->
105+
<td align="center" valign="middle" style="width: 25%; padding: 5px;" >
106+
<img src="pics/projects_publications/fireredchat.jpg" alt="Intro image" class="middle" style="max-height: 120px; width: auto;">
107+
</td>
108+
<!-- Intro part -->
109+
<td align="left" valign="middle" style="padding-left: 15px; padding-top: 10px; padding-bottom: 10px;">
110+
<!-- Title -->
111+
<b>FireRedChat: A Fully Self-Hosted Solution for Full-Duplex Voice Interaction</b>
112+
<br>
113+
<!-- Authors -->
114+
Junjie Chen, Yao Hu, Junjie Li, Kangyue Li, Kun Liu, Wenpeng Li, Xu Li, Ziyuan Li, Feiyu Shen, Xu Tang, Manzhen Wei, Yichen Wu, Fenglong Xie, Kaituo Xu, Kun Xie
115+
<br>
116+
<!-- Footnote -->
117+
<a href="https://arxiv.org/abs/2509.06502" class="footnote_btn"><b>ARXIV</b></a>
118+
<a href="https://github.com/FireRedTeam/FireRedChat" class="footnote_btn"><b>CODE</b></a>
119+
<a href="https://fireredteam.github.io/demos/firered_chat/" class="footnote_btn"><b>DEMO</b></a>
120+
</td>
121+
</tr>
122+
<!-- Data row 2 -->
123+
<tr>
124+
<!-- Image -->
125+
<td align="center" valign="middle" style="width: 25%; padding: 5px;" >
126+
<img src="pics/projects_publications/ivc_prune.jpg" alt="Intro image" class="middle" style="max-height: 120px; width: auto;">
127+
</td>
128+
<!-- Intro part -->
129+
<td align="left" valign="middle" style="padding-left: 15px; padding-top: 10px; padding-bottom: 10px;">
130+
<!-- Title -->
131+
<b>IVC-PRUNE: REVEALING THE IMPLICIT VISUAL COORDINATES IN LVLMS FOR VISION TOKEN PRUNING</b>
132+
<br>
133+
<!-- Authors -->
134+
Zhichao Sun, Yidong Ma, Gang Liu, Yibo Chen, Xu Tang, Yao Hu, Yongchao Xu
135+
<br>
136+
<!-- Footnote -->
137+
<a href="https://arxiv.org/abs/2602.03060" class="footnote_btn"><b>ARXIV</b></a>
138+
<a href="https://github.com/FireRedTeam/IVC-Prune" class="footnote_btn"><b>CODE</b></a>
139+
</td>
140+
</tr>
141+
142+
</tbody>
143+
</table>
144+
</div>
145+
146+
<div class="container pt-5 mt-5 shadow-lg p-5 mb-5 bg-white rounded">
147+
<h2 id="OpenSourceProjects" style="text-align: center;">Publications</h2>
148+
<table border="0" cellPadding="2" style="width: 100%;">
149+
<tbody>
150+
<!-- Data row 1 -->
151+
<tr>
152+
<!-- Image -->
153+
<td align="center" valign="middle" style="width: 25%; padding: 5px;" >
154+
<img src="pics/projects_publications/hymirec.jpg" alt="Intro image" class="middle" style="max-height: 120px; width: auto;">
155+
</td>
156+
<!-- Intro part -->
157+
<td align="left" valign="middle" style="padding-left: 15px; padding-top: 10px; padding-bottom: 10px;">
158+
<!-- Title -->
159+
<b>HyMiRec: A Hybrid Multi-interest Learning Framework for LLM-based Sequential Recommendation</b>
160+
<br>
161+
<!-- Authors -->
162+
Jingyi Zhou, Cheng Chen, Kai Zuo, Manjie Xu, Zhendong Fu, Yibo Chen, Xu Tang, Yao Hu
163+
<br>
164+
<!-- Conference -->
165+
<i>(WWW) The ACM Web Conference</i>
166+
<br>
167+
<!-- Footnote -->
168+
<a href="https://arxiv.org/pdf/2510.13738" class="footnote_btn"><b>ARXIV</b></a>
169+
</td>
170+
</tr>
171+
<!-- Data row 2 -->
172+
<tr>
173+
<!-- Image -->
174+
<td align="center" valign="middle" style="width: 25%; padding: 5px;" >
175+
<img src="pics/projects_publications/ivc_prune.jpg" alt="Intro image" class="middle" style="max-height: 120px; width: auto;">
176+
</td>
177+
<!-- Intro part -->
178+
<td align="left" valign="middle" style="padding-left: 15px; padding-top: 10px;">
179+
<!-- Title -->
180+
<b>IVC-PRUNE: REVEALING THE IMPLICIT VISUAL COORDINATES IN LVLMS FOR VISION TOKEN PRUNING</b>
181+
<br>
182+
<!-- Authors -->
183+
Zhichao Sun, Yidong Ma, Gang Liu, Yibo Chen, Xu Tang, Yao Hu, Yongchao Xu
184+
<br>
185+
<!-- Conference -->
186+
<i>(ICLR) The International Conference on Learning Representations</i>
187+
<br>
188+
<!-- Footnote -->
189+
<a href="https://arxiv.org/abs/2602.03060" class="footnote_btn"><b>ARXIV</b></a>
190+
<a href="https://github.com/FireRedTeam/IVC-Prune" class="footnote_btn"><b>CODE</b></a>
191+
</td>
192+
</tr>
193+
194+
</tbody>
195+
</table>
196+
</div>
197+
198+
<!--
88199
<div class="container pt-5 mt-5 shadow-lg p-5 mb-5 bg-white rounded">
89200
<h2 id="Highlights" style="text-align: center;">News</h2>
90201
<p style="text-align: left;" >
@@ -106,6 +217,7 @@ <h2 id="Highlights" style="text-align: center;">News</h2>
106217
<b>[2023.9.1]</b> We rank 1st in spoke task measursing speaker similarity at Blizzard Challenge 2023 <a href="https://feng-long.github.io/post/bc-fireredtts/ ">[link]</a>
107218
</p>
108219
</div>
220+
-->
109221

110222
<!-- <div class="container pt-5 mt-5 shadow-lg p-5 mb-5 bg-white rounded">
111223
<h2 id="zero-shot-icl-samples" style="text-align: center;">Publications</h2>

‎pics/projects_publications/fireredchat.jpg‎

103 KB
Loading

‎pics/projects_publications/hymirec.jpg‎

284 KB
Loading

‎pics/projects_publications/ivc_prune.jpg‎

247 KB
Loading

0 commit comments

Comments
 (0)