Added comprehensive RAG research papers including:
- RAG-Anything: All-in-One multimodal RAG framework
- ComoRAG: Cognitive-inspired memory-organized RAG
- NodeRAG: Graph-based RAG with heterogeneous nodes
- UniversalRAG: Multi-corpora diverse modality RAG
- Agentic RAG survey: Deep reasoning systems overview
- Vision-Guided Chunking: Multimodal document understanding
- SitEmb-v1.5: Improved context-aware dense retrieval

Updated date range from Feb 2025 to October 2025

Created complete evaluation research table covering 47 papers from Jan-Oct 2025:
- LLM Judges & Automated Evaluation (7 papers)
- Benchmarks & Datasets (6 papers)
- Domain-Specific Evaluation (9 papers)
- Multimodal Evaluation (12 papers)
- Reasoning & Cognitive Evaluation (9 papers)
- Evaluation Methodologies (6 papers)
- Robustness & Safety Evaluation (3 papers)
- Evaluation Surveys (6 papers)

Table includes neutral descriptions, accurate abstracts, and proper categorization
Covers major evaluation advances including SuperGPQA, VisuLogic, CompassVerifier,
Preference Leakage detection, and multimodal benchmarks

removed repetitive content

Added clarifications regarding course claims and instructor background to ensure accurate expectations for participants.