IDL 11-785 Spring 2024 Projects

Below is a table listing the projects along with their reports and videos.

Project Title Report Video
Enabling Large Language Models as Intelligent Agents Download Report Watch Video
Advancing Beat Detection Performance through Unprecedented Datasets and Generative Model-based Feature Extraction Download Report Watch Video
Enhancing Mathematical Reasoning in LLMs Download Report Watch Video
Text to Image Generation using Latent Diffusion Download Report Watch Video
Enhancing Mathematical Proficiency in LLM Through Transfer Learning Download Report Watch Video
Face Swapping with SimSwap+ Download Report Watch Video
Dynamic Multimodal Inference Download Report Watch Video
Optimizing Texture Analysis for Improved AI-Generated Image Detection: An Enhanced PatchCraft Approach Download Report Watch Video
Mixture-of-Experts Model for Code Generation Download Report Watch Video
Advancing Interpretability in AI: An Implementation of Neural-Symbolic Visual Question Answering Download Report Watch Video
Audio Visual Emotion Detection Download Report Watch Video
MediCodeNet: Deep Learning for Medical Code Generation from MIMIC 3 Text Data Download Report Watch Video
Pancreatic Cancer Prediction Download Report Watch Video
Silence the Noise: Spectrogram-Based Speech Enhancement Download Report Watch Video
The Internal State of an LLM Knows When It's Lying Download Report Watch Video
Stock Predictive Model Download Report Watch Video
ChatDoctor : An AI Chatbot Fine-Tuned for Medical Queries Download Report Watch Video
Enhancing Text-Audio Generation By Music Classification And RAG Download Report Watch Video
Embedding-based Music Emotion Recognition Download Report Watch Video
WAME: Waveform Music Editor a MusicLLM model for music editing Download Report Watch Video
Text-audio guided video generation Download Report Watch Video
Multimodal Vehicle-to-Vehicle Beam Prediction Download Report Watch Video
Advancing visual engagement through text-based diffusion-generated imagery Download Report Watch Video
Speech to Speech Machine Translation Using Different Modalities for Low Resource Languages Download Report Watch Video
What do you know? LLM Self Knowledge Download Report Watch Video
Drone Control with Reinforcement Learning Download Report Watch Video
DeepFit Download Report Watch Video
Talk to Nerf Download Report Watch Video
Efficiently Scaling Selective Kernel Attention TDNNs for Learning Speaker Embeddings Download Report Watch Video
Reinforcement Learning for Time-Series Forecasting Download Report Watch Video
CLIP4CLIP++ Text-Video Retrieval Project Download Report Watch Video
View-Consistent 3D Super-Resolution Download Report Watch Video
Neural Network Ensemble for Harmful Brain Activity Classification Download Report Watch Video
LLM-based end-to-end ST for IWSLT 24’ simultaneous track Download Report Watch Video
A Deep Learning Approach to Cultural Storytelling Download Report Watch Video
Multimodal Object Detection by Channel Switching and Spatial Attention: an Analysis Download Report Watch Video
Integrating Myers-Briggs Personality Types into Text Generation Download Report Watch Video
A Deep Learning Approach To Rapid and Accurate Surrogate Modelling of Finite Element Analysids Download Report Watch Video
Smart Sorter: Neural Network-Enhanced Recycling Bin Download Report Watch Video