Muhammad Akhtar Munir
9 papers · 2021–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Bronze 🗺️ Taxonomy Completionist (28) 🧬 Topic Evolution
📈
Trend Setter
🔥
Unstoppable · Bronze
Venues
Top co-authors
Research topics
Deep Learning
(8)
Computer Vision
(7)
Machine Learning
(7)
Analysis
(6)
Learning Types · Deep Learning
(6)
Artificial Intelligence
(4)
Application Areas
(4)
Core AI
(4)
Learning Types · Machine Learning
(3)
Optimization & Theory
(3)
Domain-Specific
(2)
Models
(2)
Data Science & Analytics
(1)
Natural Language Processing
(1)
Applications
(1)
Keywords
object detection
(5)
vision-language model
(4)
model calibration
(3)
confidence calibration
(2)
domain adaptation
(2)
uncertainty quantification
(2)
remote sensing
(2)
calibration error
(2)
domain shift
(2)
instruction tuning
(1)
pseudo labeling
(1)
multispectral imaging
(1)
data augmentation
(1)
scene understanding
(1)
loss function
(1)
self-supervised learning
(1)
object counting
(1)
earth observation
(1)
text embedding
(1)
change detection
(1)
Papers
Towards Calibrating Prompt Tuning of Vision- Language Models
CVPR 2026
EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues
CVPR 2025
GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks
ICCV 2025
O-TPT: Orthogonality Constraints for Calibrating Test-time Prompt Tuning in Vision-Language Models
CVPR 2025
Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment
CVPR 2024
Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection
CVPR 2023
Cal-DETR: Calibrated Detection Transformer
NeurIPS 2023
Towards Improving Calibration in Object Detection Under Domain Shift
NeurIPS 2022
SSAL: Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection
NeurIPS 2021