Muhammad Haris Khan

TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation

MMClima: A Framework for Multimodal Climate Science Data and Evaluation

Tell me Habibi, is it Real or Fake?

A-TPT: Angular Diversity Calibration Properties for Test-Time Prompt Tuning of Vision-Language Models

Foreground Confusion under Domain Shift: The Hidden Bottleneck in Source‑Free Domain Adaptive Object Detection

TOWARDS CALIBRATING PROMPT TUNING OF VISION- LANGUAGE MODELS

ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks

DCRM-ViT: Domain Conditioned Residual Modulation for Multi-Domain Vision Transformers

ViT Fine-tuning Vulnerability to Label Noise

Towards Adapting Vision-Language Models for Semi-Supervised Domain Generalization

SegMASt3R: Geometry Grounded Segment Matching

Diffusion-Guided Graph Data Augmentation

Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning

PerSense: Personalized Instance Segmentation in Dense Images

SynFER: Towards Boosting Facial Expression Recognition with Synthesis Data