start adding the new projects

src/portfolio/data/projectData.ts

@@ -1,12 +1,48 @@
 import {ProjectArguments, SkillEnum} from "@/src/portfolio/helpers/Project";
 
 const projectData : ProjectArguments[] = [
+	{
+		imagePath: "expertAgents.png",
+		tech: [
+			SkillEnum.machineLearning,
+			SkillEnum.research,
+			SkillEnum.python,
+			SkillEnum.numpy,
+			SkillEnum.dataEngineering,
+			SkillEnum.nlp
+		],
+		title: "Research Review of Neural Techniques for low-resource language translation",
+		text: "In this work, I explore a practical and cost-effective approach to improving how AI models interact with external tools and APIs. Instead of relying on large, expensive models or complex zero-shot learning methods, I utilize a modular pipeline using smaller, specialized components (Planner, Caller, Summariser) trained separately. I introduce to it a hard routing agent system that assigns tasks to expert adapters based on API categories, the system achieves performance that surpasses much larger closed-source models on a key benchmark. This approach enables more efficient, decentralized training and has potential applications beyond the tool-use QA task."
+	},
+	{
+		imagePath: "latviaEstimation.png",
+		title: "Deep Learning for Real Estate Valuation - Introducing a novel normalization technique",
+		tech: [
+			SkillEnum.machineLearning,
+			SkillEnum.research,
+			SkillEnum.python,
+			SkillEnum.numpy,
+			SkillEnum.dataEngineering,
+			SkillEnum.computerVision
+		],
+		access: "/DNNpropertyEstimation.pdf",
+		text: "Conducted within a group of three, this project presents a novel deep learning approach to predicting apartment prices using both images and structured data. The model combines feed-forward and DenseNet convolutional networks, enhanced through transfer learning and advanced regularization techniques. To address regional and temporal variations in the housing market, we introduced a geo-temporally normalized loss function—an innovation tailored for real-world market dynamics. Uniquely, the study also incorporates transport and point-of-interest maps as part of the feature set. Evaluated on a partially self-collected Latvian real estate dataset, the system achieved a strong R² score of 0.7287, surpassing previous methods in the field."
+	},
+	{
+		imagePath: "ipp.png",
+		title: "Research Proposal: Multi-LLM Tool Use – Task Splits and Fine-Tuning Strategies",
+		tech: [
+			SkillEnum.machineLearning,
+			SkillEnum.research
+		],
+		text: "This 2025 research proposal explores new ways to enhance tool use in small language models by distributing tasks across multiple fine-tuned agents. Building on recent advances in parameter-efficient fine-tuning (PEFT), the proposed study investigates novel task divisions and tuning strategies to improve the effectiveness of multi-agent LLM systems. While still in the proposal stage, this work aims to contribute to the growing field of tool-augmented AI by making small models more capable and cost-efficient.",
+		access: "/ResearchReview.pdf"
+	},
 	{
 		imagePath: "researchReview.png",
 		title: "Research Review of Neural Techniques for low-resource language translation",
 		tech: [
 			SkillEnum.machineLearning,
-			SkillEnum.latex,
 			SkillEnum.research
 		],
 		text: "As part of my Master's program, I had the opportunity to conduct an in-depth research review on \"Neural Techniques for Low-Resource Language Translation,\" which received excellent marks across all criteria. By critically evaluating the current state of the art in this field, I gained valuable insights into the potential of neural machine translation to break down language barriers and enable better communication across different cultures and communities. I am proud to showcase this project on my website and contribute to the ongoing efforts to improve low-resource language translation. This report was marked as 'excellent' for every criterion assessed in this course.",
@@ -14,7 +50,7 @@ const projectData : ProjectArguments[] = [
 	},
 	{
 		imagePath: "naturalComputing.png",
-		title: "Natural Computing: Implementing and analysis PSO, GA and GP",
+		title: "Natural Computing: Implementing and analysis of PSO, GA and GP",
 		tech: [
 			SkillEnum.python,
 			SkillEnum.numpy,

src/portfolio/helpers/Project.tsx

@@ -37,6 +37,8 @@ export enum SkillEnum {
 	photoshop = "photo-editing",
 	machineLearning = "machine learning",
 	computerVision = "computer vision",
+	dataEngineering = "data engineering",
+	nlp = "natural language processing",
 	latex = "LATEX",
 	research = "research",
 	polish = "Polish",