Research & experiments

Questions I've explored through prototypes, benchmarks, and experiments, mostly around ML/VLM robustness and large-scale software analysis. These are engineering investigations, not peer-reviewed publications.

• Large-Scale Bug Prediction

  An end-to-end research project analyzing more than 700,000 source files across 10 major Python repositories (Django, NumPy, Pandas, Flask) for bug prediction.

  Big Data · Research · Machine Learning

• AI in Software Engineering

  Research on applying AI techniques to software-engineering problems.

  Research · AI · SE

• Research Paper

  An academic research paper repository.

  Research · LaTeX

• VLM Failure Modes

  An investigation of whether Vision-Language Model uncertainty (such as entropy) actually rises on noisy, ambiguous, or corrupted inputs in safety-critical settings.

  VLM · AI Safety · Research

• VLM Adversarial Defense

  An investigation of the adversarial robustness of Vision-Language Models (LLaVA-1.5-7B) against white-box PGD attacks (the Visual Injection project).

  VLM · Adversarial ML · Python

• Amnesic VLM Defense

  An investigation of why adversarial hallucinations occur in VLMs, using entropy analysis, attention visualization, and focal ablation to show they are confident, robust, and distributed rather than localized.

  VLM · Defense · Python

• Sentiment Steering GPT

  Activation steering on GPT-2 Medium to identify and manipulate a moral direction, inverting outputs on negative concepts without retraining.

  LLM · Python · NLP