3 papers
cs.LG2025
Accuracy-Constrained CNN Pruning for Efficient and Reliable EEG-Based Seizure Detection
Mounvik K, N Harshit
Deep learning models, especially convolutional neural networks (CNNs), have shown considerable promise for biomedical signals such as EEG-based seizure detection. However, these mo…
cs.LG2025
Counterfactual Reward Model Training for Bias Mitigation in Multimodal Reinforcement Learning
Sheryl Mathew, N Harshit
In reinforcement learning with human feedback (RLHF), reward models can efficiently learn and amplify latent biases within multimodal datasets, which can lead to imperfect policy o…
cs.LG2025
Improving Real-Time Concept Drift Detection using a Hybrid Transformer-Autoencoder Framework
N Harshit, K Mounvik
In applied machine learning, concept drift, which is either gradual or abrupt changes in data distribution, can significantly reduce model performance. Typical detection methods,su…