Below is a table listing the projects along with their reports and videos.
| Project Title | Report | Video |
|---|---|---|
| Reprogramming Multimodality | Download Report | Watch Video |
| Stable Quantization-Aware Training for Vision-Language Models | Download Report | Watch Video |
| Invisible Watermarking: Attacks and Robustness | Download Report | Watch Video |
| McToT: Monte Carlo Enhanced Tree of Thought | Download Report | Watch Video |
| Fairness in Federated Learning | Download Report | Watch Video |
| Expanding StyleCLIP: Enhancing Text-Driven Image Manipulation Beyond Facial Datasets | Download Report | Watch Video |
| Locally Connected Layers for Robust Speech and Audio Models | Download Report | Watch Video |
| MultiPose Fusion: Single-view 3D Reconstruction Using Diffusion Models with Flexible Camera Pose | Download Report | Watch Video |
| Understanding Disease Features in CXR Images Using XAI for Enhanced Diagnosis Model | Download Report | Watch Video |
| Decoding EEG Speech Perception with Transformers and VAE-based Data Augmentation | Download Report | Watch Video |
| Integrating Diffusion Processes for Improved Local Context Modeling in Time Series | Download Report | Watch Video |
| Image Quality and Abstract Perception Evaluation | Download Report | Watch Video |
| GAN-based Cross-Modality Medical Image Synthesis for Prostate Cancer | Download Report | Watch Video |
| MAML*: Improving Model-Agnostic Meta-Learning With Noise Injections | Download Report | Watch Video |
| Lung Cancer Detection for Better Efficiency | Download Report | Watch Video |
| Medical Visual Question Answering: Improving Answer Quality on Multimodal Datasets with a Generative Output Layer | Download Report | Watch Video |
| Improving SSVEP Spellers with Data Augmentation and Language Models | Download Report | Watch Video |
| On Adversarial Robustness and Out-of-Distribution Robustness of Large Language Models | Download Report | Watch Video |
| Optimal Joint Moments for Robotic Lower Limb Exoskeleton | Download Report | Watch Video |
| Diffusion Personalization for 3DGS | Download Report | Watch Video |
| Efficient Referring Image Segmentation | Download Report | Watch Video |
| Enhancing CvT with RoPE and Deformable Attention | Download Report | Watch Video |
| Training Language Models to Self Correct via Reinforcement Learning | Download Report | Watch Video |
| Distilling Temporal Relation for Speech Self-Supervised Learning Model Compression | Download Report | Watch Video |
| Robust Audio Watermarking | Download Report | Watch Video |
| Automated Defect Detection in Printed Circuit Boards (PCBs) | Download Report | Watch Video |
| Predicting TCR-Epitope Binding with Fine-Tuned Protein Language Models and Contrastive Learning | Download Report | Watch Video |
| Training Humanoid Robot Hand To Rotate Block Using Deep Reinforcement Learning | Download Report | Watch Video |
| Efficient Vision-Language Captioning for Real-Time Applications | Download Report | Watch Video |
| Deep Reinforcement Learning-Based Mobile Robot Navigation in Social Spaces | Download Report | Watch Video |
| Mining Mathematical Misconceptions in Multiple-Choice Questions using NLP | Download Report | Watch Video |
| Hallucination Detection for Audio Language Models | Download Report | Watch Video |
| Mitigating Social Bias in Large Language Models By Self-Improvement | Download Report | Watch Video |
| AttenPool: A Novel Attention-Based Pooling Mechanism for Materials Property Prediction | Download Report | Watch Video |
| ala-IDL-in | Download Report | Watch Video |
| Attention-Based Audio Entailment Language Model | Download Report | Watch Video |
| Context Autoencoders for Pretraining Foundation Models for Satellite Imagery Tasks | Download Report | Watch Video |
| 3D Reconstruction Pipeline for Neural Circuitry | Download Report | Watch Video |
| CL-MSDNet: Cognitive Load Features based Multi-Modal Sarcasm Detection Network | Download Report | Watch Video |
| Accelerating POCO Inference in 3D Reconstruction of Point Clouds | Download Report | Watch Video |
| Sketch AI | Download Report | Watch Video |
| Enhancing Weather Forecasting Using Physics-Informed Neural ODEs | Download Report | Watch Video |
| Enhancing Machine Unlearning Precision through Integrated Gradient Saliency in Multi-class Image Classification Models | Download Report | Watch Video |
| Automated Stock Trading using Deep Reinforcement Learning with Social Media Sentiment Analysis | Download Report | Watch Video |
| Predicting the Level of Problematic Internet Usage Among Children | Download Report | Watch Video |
| KinyarMedASR: Enhancing Kinyarwanda Medical Speech Recognition | Download Report | Watch Video |
| Image-Text Retrieval Using ConvNeXt and Local-Global Scene Graph Matching | Download Report | Watch Video |
| Text Style Transfer | Download Report | Watch Video |
| Customized Music Style Transfer | Download Report | Watch Video |
| The Classification of Emotion and Music of SongComposer Project | Download Report | Watch Video |
| Spotify Playlist Recommendation | Download Report | Watch Video |
| InfinityGPT: Training Large Language Models for Any-To-Any Generation | Download Report | Watch Video |
| Attacking Voice Anonymization Systems for the Future of Voice Privacy | Download Report | Watch Video |
| Deep Learning in Elixir: An Investigation | Download Report | Watch Video |
| Scalable Adversarial Mixing for Enhanced Manifold Learning in Speaker Verification | Download Report | Watch Video |