I'm Pietro De Angeli

Reimplemented the paper Efficient Temporally-Aware DeepFake Detection using H.264 Motion Vectors. Matched the reported accuracy (71%) while reducing inference cost by replacing MTCNN with a lightweight YuNet-based face detector.

Extended the paper Layered Image Vectorization via Semantic Simplification by introducing radial gradients, achieving a +44% improvement in CLIP image score while reducing the average number of generated vector elements (-3% paths and -8% points).

Developed a fake news detection classifier (logistic classification and Neural network) with OpenAI text embeddings. Reached an accuracy of 99% on a toy dataset.

Improved a GNN-based Max-k-Cut solver by hybridizing a Relax-Optimize-and-Sample (ROS) pipeline with Genetic Algorithms and Ant Colony Optimization. On 48 large-scale Gset instances (up to 20k nodes, k = 2, 3, 10), bio-inspired methods consistently outperform the learning-only baseline, with up to +1.24% average improvement and best performance on k = 10 (≈ 79% of instances).

Task-oriented AI travel planner implemented as a hybrid LLM-based dialogue system. The agent supports flight, accommodation, and activity planning through multi-turn conversations using slot-filling, intent splitting for over-informative inputs, and slot carryover across related bookings. It combines LLM-based (Llama 3.1) NLU/NLG with a constrained, schema-driven dialogue manager for controllable behavior, explicit confirmation-before-booking, and robust fallback handling. Integrated with Amadeus APIs for hotels and activities.

Fine-tuned an English pretrained ASR model to Italian using NVIDIA NeMo, demonstrating effective cross-lingual transfer and achieving performance (CER: 4%) comparable to the official Italian QuartzNet model.

Designed a multilingual speaker diarization system using NVIDIA NeMo pretrained models, integrating ASR, and Speaker Identification for media analysis.