diff --git a/index.html b/index.html
index f54d700..961e388 100755
--- a/index.html
+++ b/index.html
@@ -1508,21 +1508,54 @@
optimization pipeline and pointer-based weight mapping system
- graph LR
- subgraph "Traditional Storage"
- A1["Weight Matrix (4.2B values)"] --> B1["Raw Storage (16.8 GB FP32)"]
- B1 --> C1["Many Duplicate Values (Redundant Memory)"]
- end
- subgraph "Moxiegen Pointer Mapping"
- A2["Weight Matrix (4.2B values)"] --> B2["Scan & Hash All Values"]
- B2 --> C2["Unique Value Pool (~450M values)"]
- C2 --> D2["Pointer Index (Map positions to IDs)"]
- D2 --> E2["Compressed Storage (~2.1 GB Total)"]
- end
- style B2 fill:#064e3b,color:#f8fafc,stroke:#34d399
- style C2 fill:#78350f,color:#f8fafc,stroke:#fbbf24
- style E2 fill:#065f46,color:#f8fafc,stroke:#34d399
+
+
Figure 2: Comparison of traditional weight storage versus Moxiegen's
pointer-based deduplication
@@ -1600,21 +1633,24 @@
Figure 3: Memory Efficiency Breakdown
Figure 3: Dramatic memory reduction achieved through pointer-based weight
@@ -1679,60 +1715,62 @@
Figure 4: Energy Consumption Comparison
-
-