docs: rename cost efficiency paper to Hybrid LLM, add BibTeX references section, and update PDF paths to docs/article/

README.md

@@ -64,7 +64,7 @@ InferRoute is designed for high-throughput, low routing overhead, and self-heali
 
 InferRoute integrates the core routing methodologies and trade-off evaluation principles from the research paper:
 > **ROUTERBENCH: A Benchmark for Multi-LLM Routing System** (by Martian / [withmartian/routerbench](https://github.com/withmartian/routerbench)).  
-> 📄 **[Download RouterBench Paper PDF](docs/A_Benchmark_for_Multi_LLM_Routing_System.pdf)**
+> 📄 **[Download RouterBench Paper PDF](docs/article/A_Benchmark_for_Multi_LLM_Routing_System.pdf)**
 
 ### 1. Mathematical Scoring & Optimization
 Predictive routing is formulated as choosing a backend $m$ that maximizes the utility score for a prompt $x$:
@@ -96,7 +96,7 @@ A smart, content-aware learned router (MLP/KNN) will push the Pareto frontier to
 
 InferRoute integrates the cost-performance optimization concepts from the paper:
 > **FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance** (by Stanford University / arXiv:2305.05196).  
-> 📄 **[Download FrugalGPT Paper PDF](docs/How_to_Use_Large_Language_Models.pdf)** | 📄 **[Download Cost Efficiency PDF](docs/cost_efficiency.pdf)** | 📄 **[Download InferRoute Project Plan PDF](docs/InferRoute_Project_Plan.pdf)**
+> 📄 **[Download FrugalGPT Paper PDF](docs/article/How_to_Use_Large_Language_Models.pdf)** | 📄 **[Download Hybrid LLM Routing Paper PDF](docs/article/cost_efficiency.pdf)** | 📄 **[Download InferRoute Project Plan PDF](docs/InferRoute_Project_Plan.pdf)**
 
 FrugalGPT identifies three main classes of cost-saving methods:
 1. **Prompt Adaptation**: Reduces input tokens dynamically. In InferRoute, when routing to cheap local backends (Ollama/vLLM), the **Prompt Adapter** (`prompt_adapter.py`) automatically compresses prompt sizes by pruning few-shot examples, restoring full prompts when upgrading to premium models.

cost efficienct.pdf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c0ebc21073112b8f8e51c7ea279eeac4d5b62be88c69a5cd2bccc2d58ec28cbb
-size 4833670

docs/index.html

@@ -785,22 +785,22 @@
                 <h2>📚 Original Research Papers & Download Hub</h2>
                 <p>Read or download the full research publications and project blueprints associated with this routing engine:</p>
                 <div class="paper-grid" style="display: grid; grid-template-columns: repeat(2, 1fr); gap: 1rem; margin-top: 1.5rem;">
-                    <a href="A_Benchmark_for_Multi_LLM_Routing_System.pdf" download class="sub-card" style="display: flex; flex-direction: column; text-decoration: none; transition: all 0.3s; padding: 1.5rem; background: rgba(0, 0, 0, 0.02); border: 1px solid var(--border-color); border-radius: 12px; color: var(--text-primary);">
+                    <a href="article/A_Benchmark_for_Multi_LLM_Routing_System.pdf" download class="sub-card" style="display: flex; flex-direction: column; text-decoration: none; transition: all 0.3s; padding: 1.5rem; background: rgba(0, 0, 0, 0.02); border: 1px solid var(--border-color); border-radius: 12px; color: var(--text-primary);">
                         <span style="font-size: 1.5rem; margin-bottom: 0.5rem;">📄</span>
                         <span style="font-family: var(--font-outfit); font-weight: 700; font-size: 1.1rem; color: var(--text-primary); margin-bottom: 0.25rem;">RouterBench Paper</span>
                         <span style="font-size: 0.8rem; color: var(--text-secondary); margin-bottom: 0.75rem;">A Benchmark for Multi-LLM Routing System (Martian, 2024)</span>
                         <span style="align-self: flex-start; background: rgba(139, 92, 246, 0.15); border: 1px solid rgba(109, 40, 217, 0.2); color: var(--accent-violet); font-size: 0.75rem; font-weight: 600; padding: 0.25rem 0.65rem; border-radius: 6px;">Download PDF</span>
                     </a>
-                    <a href="How_to_Use_Large_Language_Models.pdf" download class="sub-card" style="display: flex; flex-direction: column; text-decoration: none; transition: all 0.3s; padding: 1.5rem; background: rgba(0, 0, 0, 0.02); border: 1px solid var(--border-color); border-radius: 12px; color: var(--text-primary);">
+                    <a href="article/How_to_Use_Large_Language_Models.pdf" download class="sub-card" style="display: flex; flex-direction: column; text-decoration: none; transition: all 0.3s; padding: 1.5rem; background: rgba(0, 0, 0, 0.02); border: 1px solid var(--border-color); border-radius: 12px; color: var(--text-primary);">
                         <span style="font-size: 1.5rem; margin-bottom: 0.5rem;">📄</span>
                         <span style="font-family: var(--font-outfit); font-weight: 700; font-size: 1.1rem; color: var(--text-primary); margin-bottom: 0.25rem;">FrugalGPT Paper</span>
                         <span style="font-size: 0.8rem; color: var(--text-secondary); margin-bottom: 0.75rem;">How to Use Large Language Models While Reducing Cost and Improving Performance (Stanford, 2023)</span>
                         <span style="align-self: flex-start; background: rgba(139, 92, 246, 0.15); border: 1px solid rgba(109, 40, 217, 0.2); color: var(--accent-violet); font-size: 0.75rem; font-weight: 600; padding: 0.25rem 0.65rem; border-radius: 6px;">Download PDF</span>
                     </a>
-                    <a href="cost_efficiency.pdf" download class="sub-card" style="display: flex; flex-direction: column; text-decoration: none; transition: all 0.3s; padding: 1.5rem; background: rgba(0, 0, 0, 0.02); border: 1px solid var(--border-color); border-radius: 12px; color: var(--text-primary);">
+                    <a href="article/cost_efficiency.pdf" download class="sub-card" style="display: flex; flex-direction: column; text-decoration: none; transition: all 0.3s; padding: 1.5rem; background: rgba(0, 0, 0, 0.02); border: 1px solid var(--border-color); border-radius: 12px; color: var(--text-primary);">
                         <span style="font-size: 1.5rem; margin-bottom: 0.5rem;">📄</span>
-                        <span style="font-family: var(--font-outfit); font-weight: 700; font-size: 1.1rem; color: var(--text-primary); margin-bottom: 0.25rem;">Cost Efficiency Paper</span>
-                        <span style="font-size: 0.8rem; color: var(--text-secondary); margin-bottom: 0.75rem;">Cost-efficient execution strategies of Large Language Models.</span>
+                        <span style="font-family: var(--font-outfit); font-weight: 700; font-size: 1.1rem; color: var(--text-primary); margin-bottom: 0.25rem;">Hybrid LLM Routing Paper</span>
+                        <span style="font-size: 0.8rem; color: var(--text-secondary); margin-bottom: 0.75rem;">Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing (IBM / Tsinghua, 2024)</span>
                         <span style="align-self: flex-start; background: rgba(139, 92, 246, 0.15); border: 1px solid rgba(109, 40, 217, 0.2); color: var(--accent-violet); font-size: 0.75rem; font-weight: 600; padding: 0.25rem 0.65rem; border-radius: 6px;">Download PDF</span>
                     </a>
                     <a href="InferRoute_Project_Plan.pdf" download class="sub-card" style="display: flex; flex-direction: column; text-decoration: none; transition: all 0.3s; padding: 1.5rem; background: rgba(0, 0, 0, 0.02); border: 1px solid var(--border-color); border-radius: 12px; color: var(--text-primary);">
@@ -811,6 +811,64 @@
                     </a>
                 </div>
             </div>
+
+            <!-- Academic Bibliography & References -->
+            <div class="glass-card" style="margin-top: 2rem;">
+                <h2>📚 Academic Bibliography & References</h2>
+                <p>Formal scientific citations for the core research papers referenced during the design and optimization of the InferRoute gateway:</p>
+                
+                <div style="display: flex; flex-direction: column; gap: 1.5rem; margin-top: 1.5rem;">
+                    
+                    <div class="sub-card" style="background: rgba(0,0,0,0.01);">
+                        <h4 style="font-family: var(--font-outfit); font-weight: 700; color: var(--text-primary); margin-bottom: 0.5rem;">1. FrugalGPT (Stanford University)</h4>
+                        <p style="font-size: 0.9rem; color: var(--text-secondary); margin-bottom: 0.75rem; font-style: italic;">
+                            Chen, L., Zaharia, M., & Zou, J. (2023). FrugalGPT: How to use large language models while reducing cost and improving performance. <em>arXiv preprint arXiv:2305.05196</em>.
+                        </p>
+                        <details style="cursor: pointer; font-size: 0.85rem;">
+                            <summary style="color: var(--accent-violet); font-weight: 600; outline: none; margin-bottom: 0.5rem;">Show BibTeX Citation</summary>
+                            <pre style="background: rgba(0,0,0,0.03); padding: 0.75rem; border-radius: 6px; border: 1px solid var(--border-color); overflow-x: auto; font-family: monospace; color: var(--text-secondary);">@article{chen2023frugalgpt,
+  title={FrugalGPT: How to use large language models while reducing cost and improving performance},
+  author={Chen, Lingjiao and Zaharia, Matei and Zou, James},
+  journal={arXiv preprint arXiv:2305.05196},
+  year={2023}
+}</pre>
+                        </details>
+                    </div>
+
+                    <div class="sub-card" style="background: rgba(0,0,0,0.01);">
+                        <h4 style="font-family: var(--font-outfit); font-weight: 700; color: var(--text-primary); margin-bottom: 0.5rem;">2. RouterBench (Martian)</h4>
+                        <p style="font-size: 0.9rem; color: var(--text-secondary); margin-bottom: 0.75rem; font-style: italic;">
+                            Li, T., Martian Team, et al. (2024). RouterBench: A Benchmark for Multi-LLM Routing System. <em>arXiv preprint arXiv:2403.11164</em>.
+                        </p>
+                        <details style="cursor: pointer; font-size: 0.85rem;">
+                            <summary style="color: var(--accent-violet); font-weight: 600; outline: none; margin-bottom: 0.5rem;">Show BibTeX Citation</summary>
+                            <pre style="background: rgba(0,0,0,0.03); padding: 0.75rem; border-radius: 6px; border: 1px solid var(--border-color); overflow-x: auto; font-family: monospace; color: var(--text-secondary);">@article{li2024routerbench,
+  title={RouterBench: A Benchmark for Multi-LLM Routing System},
+  author={Li, Teh-Hsien and others},
+  journal={arXiv preprint arXiv:2403.11164},
+  year={2024}
+}</pre>
+                        </details>
+                    </div>
+
+                    <div class="sub-card" style="background: rgba(0,0,0,0.01);">
+                        <h4 style="font-family: var(--font-outfit); font-weight: 700; color: var(--text-primary); margin-bottom: 0.5rem;">3. Hybrid LLM Routing (IBM / Tsinghua)</h4>
+                        <p style="font-size: 0.9rem; color: var(--text-secondary); margin-bottom: 0.75rem; font-style: italic;">
+                            Ding, J., et al. (2024). Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing. <em>arXiv preprint arXiv:2404.14944</em>.
+                        </p>
+                        <details style="cursor: pointer; font-size: 0.85rem;">
+                            <summary style="color: var(--accent-violet); font-weight: 600; outline: none; margin-bottom: 0.5rem;">Show BibTeX Citation</summary>
+                            <pre style="background: rgba(0,0,0,0.03); padding: 0.75rem; border-radius: 6px; border: 1px solid var(--border-color); overflow-x: auto; font-family: monospace; color: var(--text-secondary);">@article{ding2024hybrid,
+  title={Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing},
+  author={Ding, Jiayi and others},
+  journal={arXiv preprint arXiv:2404.14944},
+  year={2024}
+}</pre>
+                        </details>
+                    </div>
+
+                </div>
+            </div>
         </div>
 
         <!-- Tab 2: Architecture -->