Two Vision–Language Papers Submitted to ICLR 2026

Submitted two papers to ICLR 2026 — one on Geo-Temporal Reasoning (as co-lead author) and another on Spatial Reasoning in Vision–Language Models (as co-author) — in collaboration with Qatar Computing Research Institute (QCRI) and CIOL.
These works explore robust multimodal understanding and contextual reasoning in large-scale foundation models.