Publised:
[1] T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusion[Accepted at AAAI 2026 Main Technical Track]
[2] SignFormer-GCN: Continuous sign language translation using spatio-temporal graph convolutional networks[WiML Workshop, Neurips 2025; PLOS One]
[3] Classical machine learning approach for human activity recognition using location data[UbiComp/ISWC]
Preprint:
[1] Counting Through Occlusion: Framework for Open World Amodal Counting[Submitted to CVPR 2026]
[2] LAGEA: Language Guided Embodied Agents for Robotic Manipulation[Submitted to ICLR 2026]
