activity
20242026
collaborators

14 papers

cs.AI2026

HetGPS: Scalable Graph Multi-Agent Reinforcement Learning with Physics-Anchored Adaptive Safety for EV Charging

Xiangwei Wang, Nanduni Nimalsiri, Yu Xia +2

Safety interventions for large populations of network-coupled agents must protect shared constraints without unnecessarily overriding task-oriented policy decisions. We present Het…

cs.CV2026

FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration

Thiru Thillai Nadarasar Bahavan, Sachith Seneviratne, Saman Halgamuge

Deep Neural Network (DNN) classifiers suffer from poor calibration when their softmax outputs (predictive confidence) deviate from the empirical likelihoods. This manifests itself…

cs.LG2026

Knowledge-Inclusive Adaptive Physics-Informed Neural Network for Microbial Interaction Modelling

Ravisha Rupasinghe, Rajith Vidanaarachchi, Asela Hevapathige +3

Physics-Informed Neural Network (PINN) is a way of including knowledge in the form of equations in Machine Learning methods. Beyond equations, knowledge exists in other forms, such…

cs.CV2026

Beyond Deepfake vs Real: Facial Deepfake Detection in the Open-Set Paradigm

Nadarasar Bahavan, Sachith Seneviratne, Sanjay Saha +3

Facial forgery methods such as deepfakes can be misused for identity manipulation and spreading misinformation. They have evolved alongside advancements in generative AI, leading t…

cs.CV2026

Parameter-efficient Prompt Tuning and Hierarchical Textual Guidance for Few-shot Whole Slide Image Classification

Jayanie Bogahawatte, Sachith Seneviratne, Saman Halgamuge

Whole Slide Images (WSIs) are giga-pixel in scale and are typically partitioned into small instances in WSI classification pipelines for computational feasibility. However, obtaini…

cs.LG2026

Arch-VQ: Discrete Architecture Representation Learning with Autoregressive Priors

Deshani Geethika Poddenige, Sachith Seneviratne, Asela Hevapathige +4

Existing neural architecture representation learning methods focus on continuous representation learning, typically using Variational Autoencoders (VAEs) to map discrete architectu…