7 citations · 14 across the 23 of their papers we have counts for
27 papers
HarnessNet: Feedback-driven Hierarchical Joint Harness Evolution for Multi-agent Systems
Zhaoyuan Qiu, Sachith Seneviratne, Yu Xia +1
AI agents can evolve by using environment feedback to revise their harnesses, the software managing model inputs, tool use, memory, and execution, while keeping foundation models f…
SmoothOperator: Enhancing Representations for Fine-grained Open-set Recognition via Modulated Label Smoothing
Thiru Thillai Nadarasar Bahavan, Yu Xia, Sachith Seneviratne +1
Open Set Recognition (OSR) aims to enable models to accurately classify known classes while rejecting samples from unseen classes. A key challenge in OSR lies in the inability to m…
CORDIAL: Calibrating Ordinal LLM Outputs from Few Labels
Xiangwei Wang, Peng Wang, Saman Halgamuge
A large language model (LLM) can turn a text into a distribution over an ordered scale, but that distribution is a noisy measurement: saturated, compressed or exaggerated, and bias…
When Agents Disagree: Bayesian Backward Reasoning as a Label-Free Anchor for Multi-Agent Collective Decision-Making
Ken Chen, Wei Wang, Sachith Seneviratne +2
When multiple LLM agents yield conflicting answers, the decision-making process dictates whether agent diversity improves performance or merely compounds shared errors. Existing co…
Bidirectional Multimodal Fusion of Sky Images and Time-Series for Solar Forecasting with Large Language Models
Ken Chen, Maneesha Perera, Wei Wang +3
Short-term photovoltaic (PV) power and global horizontal irradiance (GHI) forecasts are essential for effective dispatch, reserve scheduling, and grid operations. At these forecast…
Not Just Oversmoothing: Detecting the Echo Chamber Effect in Graph Neural Networks
Asela Hevapathige, Ahad N. Zehmakan, Asiri Wijesinghe +1
Oversmoothing is a well-known failure mode of Graph Neural Networks (GNNs). However, most existing diagnostics rely on global aggregation measures that fail to capture the heteroge…
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…
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…
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…
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…
MSRAMIE: Multimodal Structured Reasoning Agent for Multi-instruction Image Editing
Zhaoyuan Qiu, Ken Chen, Xiangwei Wang +3
Existing instruction-based image editing models perform well with simple, single-step instructions but degrade in realistic scenarios that involve multiple, lengthy, and interdepen…
From Specification to Architecture: A Theory Compiler for Knowledge-Guided Machine Learning
Asela Hevapathige, Yu Xia, Sachith Seneviratne +1
Theory-guided machine learning has demonstrated that including authentic domain knowledge directly into model design improves performance, sample efficiency and out-of-distribution…
Invariant-Stratified Propagation for Expressive Graph Neural Networks
Asela Hevapathige, Ahad N. Zehmakan, Asiri Wijesinghe +1
Graph Neural Networks (GNNs) face fundamental limitations in expressivity and capturing structural heterogeneity. Standard message-passing architectures are constrained by the 1-di…
Stepwise Intrinsic Rewards for Reasoning in Large Language Models
Xiangwei Wang, Wei Wang, Ken Chen +3
Reinforcement learning (RL) has become a widely used paradigm for improving the reasoning abilities of large language models (LLMs) and Vision-language models (VLMs). Sparse binary…
FRAME-C: A knowledge-augmented deep learning pipeline for classifying multi-electrode array electrophysiological signals
Nisal Ranasinghe, Dzung Do-Ha, Chathura J. Gamage +5
Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disorder characterized by motor neuron degeneration, with changes to neuronal excitability being an early phenotype…
Graph-Eq: Discovering Mathematical Equations using Graph Generative Models
Nisal Ranasinghe, Damith Senanayake, Saman Halgamuge
The ability to discover meaningful, accurate, and concise mathematical equations that describe datasets is valuable across various domains. Equations offer explicit relationships b…
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…
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…
SphOR: A Representation Learning Perspective on Open-set Recognition for Identifying Unknown Classes in Deep Learning Models
Nadarasar Bahavan, Sachith Seneviratne, Saman Halgamuge
The reliance on Deep Neural Network (DNN)-based classifiers in safety-critical and real-world applications necessitates Open-Set Recognition (OSR). OSR enables the identification o…
TT-MPD: Test Time Model Pruning and Distillation
Haihang Wu, Wei Wang, Tamasha Malepathirana +3
Pruning can be an effective method of compressing large pre-trained models for inference speed acceleration. Previous pruning approaches rely on access to the original training dat…
NeST: Neighborhood-aware semantic alignment and temporal modulation for LLM based time series forecasting
Jayanie Bogahawatte, Sachith Seneviratne, Maneesha Perera +1
Adapting Large Language Models (LLMs) trained on discrete text data, to forecast continuous time series signals is challenging. While finetuning the LLMs enables such adaptation, e…
GINN-KAN: Interpretability pipelining with applications in Physics Informed Neural Networks
Nisal Ranasinghe, Yu Xia, Sachith Seneviratne +1
Neural networks are powerful function approximators, yet their ``black-box" nature often renders them opaque and difficult to interpret. While many post-hoc explanation methods exi…
AniFaceDiff: Animating Stylized Avatars via Parametric Conditioned Diffusion Models
Ken Chen, Sachith Seneviratne, Wei Wang +7
Animating stylized avatars with dynamic poses and expressions has attracted increasing attention for its broad range of applications. Previous research has made significant progres…
Day-ahead regional solar power forecasting with hierarchical temporal convolutional neural networks using historical power generation and weather data
Maneesha Perera, Julian De Hoog, Kasun Bandara +2
Regional solar power forecasting, which involves predicting the total power generation from all rooftop photovoltaic systems in a region holds significant importance for various st…