Simplify publications layout: keep only Abstract and PDF button, add beautiful abstract cover images

Author: FlyTia

content/publications/chronological-thinking/index.md

@@ -13,29 +13,39 @@ publication_short: arXiv
 
 abstract: This work explores chronological thinking capabilities in full-duplex spoken dialogue language models, enabling more natural and coherent conversational interactions.
 
-summary: Exploring chronological thinking in full-duplex spoken dialogue language models.
-
-tags:
-  - Audio LLM
-  - Full-Duplex
-  - Spoken Dialogue
-  - Language Models
-
 featured: true
 
+# Featured image - 优美抽象画面封面建议：
+# Option 1: 彩色流体艺术（蓝紫金色）
+image:
+  url: 'https://images.unsplash.com/photo-1541701494587-cb58502866ab?w=1200&q=80'
+  caption: 'Abstract Art'
+# Option 2: 渐变水彩质感（粉紫色系）
+# image:
+#   url: 'https://images.unsplash.com/photo-1557672172-298e090bd0f1?w=1200&q=80'
+#   caption: 'Abstract Watercolor'
+# Option 3: 抽象光影纹理（暖色调）
+# image:
+#   url: 'https://images.unsplash.com/photo-1550859492-d5da9d8e45f3?w=1200&q=80'
+#   caption: 'Abstract Light'
+# Option 4: 流动色彩（多彩渐变）
+# image:
+#   url: 'https://images.unsplash.com/photo-1506259091721-347e791bab0f?w=1200&q=80'
+#   caption: 'Fluid Colors'
+# Option 5: 抽象烟雾质感（蓝橙色）
+# image:
+#   url: 'https://images.unsplash.com/photo-1553356084-58ef4a67b2a7?w=1200&q=80'
+#   caption: 'Abstract Smoke'
+
 links:
   - type: pdf
-    url: https://arxiv.org/abs/2510.05150
-  - type: source
-    url: https://arxiv.org/abs/2510.05150
+    url: https://arxiv.org/pdf/2510.05150
 
 url_pdf: 'https://arxiv.org/pdf/2510.05150'
-url_code: ''
-url_dataset: ''
-url_poster: ''
-url_project: ''
-url_slides: ''
-url_source: 'https://arxiv.org/abs/2510.05150'
-url_video: ''
----
 
+# Hide page metadata
+share: false
+show_date: false
+profile: false
+pager: false
+---

content/publications/step-audio-2/index.md

@@ -13,29 +13,22 @@ publication_short: arXiv
 
 abstract: Step-Audio 2 is the world's first industrial-grade end-to-end audio LLM with deep thinking capabilities, introducing Chain-of-Thought reasoning and audio reinforcement learning into speech models for the first time.
 
-summary: The world's first industrial-grade end-to-end audio LLM with CoT reasoning and reinforcement learning.
-
-tags:
-  - Audio LLM
-  - Chain-of-Thought
-  - Reinforcement Learning
-  - Speech Understanding
-
 featured: true
 
+# Featured image - 优美抽象画面
+image:
+  url: 'https://images.unsplash.com/photo-1550859492-d5da9d8e45f3?w=1200&q=80'
+  caption: 'Abstract Art'
+
 links:
   - type: pdf
-    url: https://arxiv.org/abs/2507.16632
-  - type: source
-    url: https://arxiv.org/abs/2507.16632
+    url: https://arxiv.org/pdf/2507.16632
 
 url_pdf: 'https://arxiv.org/pdf/2507.16632'
-url_code: ''
-url_dataset: ''
-url_poster: ''
-url_project: ''
-url_slides: ''
-url_source: 'https://arxiv.org/abs/2507.16632'
-url_video: ''
----
 
+# Hide page metadata
+share: false
+show_date: false
+profile: false
+pager: false
+---

content/publications/step-audio-aqaa/index.md

@@ -13,28 +13,22 @@ publication_short: arXiv
 
 abstract: Step-Audio-AQAA presents a fully end-to-end expressive large audio language model, pushing the boundaries of expressive speech synthesis and understanding.
 
-summary: A fully end-to-end expressive large audio language model.
-
-tags:
-  - Audio LLM
-  - Expressive Speech
-  - End-to-End Model
-
 featured: true
 
+# Featured image - 优美抽象画面
+image:
+  url: 'https://images.unsplash.com/photo-1506259091721-347e791bab0f?w=1200&q=80'
+  caption: 'Abstract Art'
+
 links:
   - type: pdf
-    url: https://arxiv.org/abs/2506.08967
-  - type: source
-    url: https://arxiv.org/abs/2506.08967
+    url: https://arxiv.org/pdf/2506.08967
 
 url_pdf: 'https://arxiv.org/pdf/2506.08967'
-url_code: ''
-url_dataset: ''
-url_poster: ''
-url_project: ''
-url_slides: ''
-url_source: 'https://arxiv.org/abs/2506.08967'
-url_video: ''
----
 
+# Hide page metadata
+share: false
+show_date: false
+profile: false
+pager: false
+---

content/publications/step-audio/index.md

@@ -13,28 +13,22 @@ publication_short: arXiv
 
 abstract: Step-Audio represents a unified approach to understanding and generation in intelligent speech interaction systems, advancing the capabilities of audio language models.
 
-summary: A unified framework for speech understanding and generation in intelligent interaction systems.
-
-tags:
-  - Audio LLM
-  - Speech Understanding
-  - Speech Generation
-
 featured: true
 
+# Featured image - 优美抽象画面
+image:
+  url: 'https://images.unsplash.com/photo-1557672172-298e090bd0f1?w=1200&q=80'
+  caption: 'Abstract Art'
+
 links:
   - type: pdf
-    url: https://arxiv.org/abs/2502.11946
-  - type: source
-    url: https://arxiv.org/abs/2502.11946
+    url: https://arxiv.org/pdf/2502.11946
 
 url_pdf: 'https://arxiv.org/pdf/2502.11946'
-url_code: ''
-url_dataset: ''
-url_poster: ''
-url_project: ''
-url_slides: ''
-url_source: 'https://arxiv.org/abs/2502.11946'
-url_video: ''
----
 
+# Hide page metadata
+share: false
+show_date: false
+profile: false
+pager: false
+---