| 
               Fahim Faisal Niloy
               
                I am a third year PhD Student at the Vision and Learning Group of University of California, Riverside. I am supervised by Dr. Amit K. Roy-Chowdhury. My PhD research focuses on efficient adaptation of foundation models, with particular emphasis on parameter efficient tuning, test-time adaptation, and optimizing deployment on edge devices. Additionally, I have strong interest in media forensics, specifically in areas such as image
and video forgery localization and deepfake detection. 
                             
              
                Email  / 
                CV  /               
                Google Scholar  / 
                LinkedIn 
               
             | 
            
            
            
            
    
        
             
        
        
            "Everything has its wonders, even darkness and silence, and I learn, whatever state I may be in, therein to be content." - Helen Keller
         
     
 | 
           
         
        
            
            | 
              Updates
               
                Aug 2025: Paper accepted at EMNLP 2025
                
                Jun 2025: Passed my oral qualifier!
                
                Jun 2025: Paper accepted at MICCAI 2025 
                
                Feb 2025: Two Papers accepted at CVPR 2025 
                 
                Sep 2024: Paper accepted at NeurIPS 2024 
                 
                Aug 2024: Paper accepted at ICPR 2024 
                 
                Jan 2024: Paper accepted at PAKDD 2024 (Oral) 
                 
                Dec 2023: Paper accepted at ICASSP 2024  
                  
                Nov 2023: Poster accepted at ACM SAC  
                  
                Oct 2023: Paper accepted at WACV 2024  
                  
                Jul 2023: Serving as a reviewer for TPAMI (IF: 23.6)  
                  
                Jun 2023: Paper accepted at ICIP 2023 
                
                Sep 2022: Started PhD at UCR 
                
               
             | 
           
          
          
          
         
        
        
           
            
              
                AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments
              
               
              Xiangyu Chang, Fahim Faisal Niloy, Sk Miraj Ahmed, Srikanth Krishnamurthy, Basak Guler, Ananthram Swami, Samet Oymak and Amit K. Roy-Chowdhury
               
               IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
               
             | 
              
           
            
              
                Towards Source-Free Machine Unlearning
              
               
              Sk Miraj Ahmed, Umit Yigit Basaran, Dripta S. Raychaudhuri, Arindam Dutta, Rohit Kundu, Fahim Faisal Niloy, Basak Guler and Amit Roy-Chowdhury
               
               IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
               
             | 
              
          
            
              
                HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models
              
               
              Trishna Chakraborty, Udita Ghosh, Xiaopan Zhang, Fahim Faisal Niloy, Yue Dong, Jiachen Li, Amit K Roy-Chowdhury, Chengyu Song
               
               Conference on Empirical Methods in Natural Language Processing (EMNLP Findings), 2025
               
             | 
              
          
            
              
                ODES: Domain Adaptation with Expert Guidance for Online Medical Image Segmentation
              
               
              Md Shazid Islam, Sayak Nag, Arindam Dutta, Fahim Faisal Niloy, Miraj Ahmed, Amit K. Roy-Chowdhury
               
               28th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2025
               
             | 
              
          
          
            
              
                CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions
              
               
              Sk Miraj Ahmed*, Fahim Faisal Niloy*, Xiangyu Chang, Dripta S. Raychaudhuri, Samet Oymak and Amit K. Roy-Chowdhury
               
               The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
               
              *equal contribution
               
             | 
              
          
            
              
                Effective Restoration of Source Knowledge in Continual Test Time Adaptation
              
               
              Fahim Faisal Niloy, Sk Miraj Ahmed, Dripta S. Raychaudhuri, Samet Oymak and Amit K. Roy-Chowdhury
               
              IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024
               
             | 
              
          
          
            
              
                Source-Free Online Domain Adaptive Semantic Segmentation of Satellite Images under Image Degradation
              
               
              Fahim Faisal Niloy, Kishor Kumar Bhaumik, Simon S. Woo
               
              IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024
               
             | 
              
          
            
              
                SSMT: Few-Shot Traffic Forecasting with Single Source Meta-Transfer
              
               
              Kishor Kumar Bhaumik, Minha Kim, Fahim Faisal Niloy, Amin Ahsan Ali, Simon S. Woo
               
              International Conference on Pattern Recognition (ICPR), 2024
               
             | 
              
          
            
              
                STLGRU: Spatio-Temporal Lightweight Graph GRU for Traffic Flow Prediction
              
               
              Kishor Kumar Bhaumik, Fahim Faisal Niloy, Saif Mahmud, Simon S. Woo
               
              Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2024 (Oral)
               
             | 
              
           
            
              
                CFL-Net: Image Forgery Localization Using Contrastive Learning
              
               
              Fahim Faisal Niloy, Kishor Kumar Bhaumik, Simon S. Woo
               
              IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023
               
             | 
              
          
            
              
                HRFNet: High-Resolution Forgery Network for Localizing Satellite Image Manipulation
              
               
              Fahim Faisal Niloy, Kishor Kumar Bhaumik, Simon S. Woo
               
              IEEE International Conference on Image Processing (ICIP), 2023
               
             | 
             
          
          
            
              
                Attention Toward Neighbors: A Context Aware Framework For High Resolution Image Segmentation
              
               
              Fahim Faisal Niloy, M. Ashraful Amin, Amin Ahsan Ali, AKM Mahbubur Rahman
               
              IEEE International Conference on Image Processing (ICIP), 2021
               
             | 
             
          
          
            
              
                A Novel Disaster Image Data-set and Characteristics Analysis using Attention Model
              
               
              Fahim Faisal Niloy, Abu Bakar Siddik Nayem, Anis Sarker, Ovi Paul, M Ashraful Amin, Amin Ahsan Ali, Moinul Islam Zaber, AKM Mahbubur Rahman
               
              International Conference on Pattern Recognition (ICPR), 2020
               
             | 
             
     
          
  
          
        
          
        
  
  
  |