Update README.md

README.md

@@ -33,17 +33,16 @@ This organization hosts resources from multiple research projects and publicatio
 
 ### Datasets for Security & Software Engineering
 - **PyResBugs** – 5,007 residual Python bugs with NL descriptions  
-- **Shellcode_IA32** – The largest curated dataset of IA-32 shellcode snippets (3 versions)  
+- **Shellcode_IA32** – The largest curated dataset of IA-32 shellcode snippets
 - **PoisonPy** – Dataset supporting targeted data-poisoning attacks  
 - **Human vs AI Code** – Defects, vulnerabilities, and complexity analysis at scale  
-- **EVIL datasets** – Exploit generation datasets (assembly & Python)
 
-### Robustness, Poisoning & Exploit Generation
-- **Offensive Code Generation Robustness** – Data augmentation framework  
-- **Context-Aware Exploits** – Benchmark for NL-to-exploit generation  
-- **AI Code Generator Poisoning** – Targeted poisoning pipelines and evaluation  
+### Robustness, Data Quality & Industrial Code Generation
+- **Residual Bug Generation from Natural Language** – Frameworks for generating realistic residual defects from NL descriptions  
+- **Impact of Data Quality on Code Models** – Empirical studies on robustness, poisoning resilience, and dataset quality  
+- **Industrial Code Generation** – Models for domain-specific code synthesis (e.g., VHDL generation from natural language)  
 
-All repositories include code, experimental scripts, datasets, and reproducibility materials.
+Our repositories include code, experimental scripts, datasets, and reproducibility materials.
 
 ---
 
@@ -52,7 +51,7 @@ All repositories include code, experimental scripts, datasets, and reproducibili
 Our work spans four interconnected areas:
 
 1. **Security of AI-generated Code**  
-   Vulnerability detection, automated patching, exploit generation, robustness testing.
+   Vulnerability detection, automated patching, exploit generation, and robustness testing.
 
 2. **Trustworthy LLM Evaluation**  
    Correctness, equivalence checking, symbolic execution, reproducible benchmarks.
@@ -78,7 +77,6 @@ A non-exhaustive list includes works presented at:
 - **Information and Software Technology (IST)**
 - **Automated Software Engineering (AUSE)**
 - **Journal of Systems and Software (JSS)**
-- **NLP4Prog Workshop**
 
 Full references are available inside each corresponding repository.