| 1/6/25 | Lecture-1-Introduction
[Video of Presentation] | Dr. Shah | <!--[Video of Presentation]--> |
| 1/8/25 | Lecture-2-Introduction Part II
[Video of Presentation] | Dr. Shah | |
| 1/13/25 | Lecture-3-Transformers
[Video of Presentation] | Dr. Shah | |
| 1/15/25 | Lecture-4-CLIP
[Video of Presentation] | Dr. Shah | |
| 1/20/25 | Martin Luther King Jr. Day No Class | | |
| 1/22/25 | Lecture-5-Visual-Language Models Introduction Part-I
[Video of Presentation] | | |
| 1/27/25 | Lecture-6-Visual-Language Models Introduction Part-II
[Video of Presentation] | Dr. Shah | |
| 1/29/25 | Lecture-7-Visual-Language Models Introduction Part-III
[Video of Presentation] | Dr. Shah | |
| 2/3/25 | Lecture-8-Visual-Language Models Introduction Part-IV
[Video of Presentation] | Dr. Shah | |
| 2/5/25 | Project Potential Ideas | Dr. Shah | |
| 2/10/25 | Lecture-10-Diffusion Models
[Video of Presentation] | Dr. Shah | |
| 2/12/25 | Lecture-11-Diffusion Models
[Video of Presentation] | Dr. Shah | |
| 2/17/25 | Lecture-12-Diffusion Models
[Video of Presentation] | Dr. Shah | |
| 2/19/25 | Paper-1 Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
[Presentation PDF]
[Video of Presentation] | Group 1 - Qingyang Liu, Inad Alqurashi, Sabbir Mollah, Ahnaf Munir, Saurabh Aggarwal | |
| 2/24/25 | Student Project Presentations Ideas | | |
| 2/26/25 | Paper-2 HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data
[Presentation PDF]
[Video of Presentation] | Group 5 - Kim, Fazil, Arman Sayan | |
| 3/3/25 | Paper-3 MLLMGUARD:A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
[Presentation PDF]
[Video of Presentation] | Group 4 - Adam Bawatneh, Zengyan Wang, Scott Spicer, Colin Houde (A) | |
| 3/5/25 | Paper-4 MULTITRUST: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models
[Presentation PDF]
[Video of Presentation] | Group 3 - Eduardo Bourget, Nathan Couch, Isaac Tuckey, Rodrigo Vena | |
| 3/10/25 | Paper-5 MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models
[Presentation PDF]
[Video of Presentation] | Group 9 - Robert Martin,Judd Brock-Edgar,Jacob Braun,Cameron Nichols,Taylor Tiedge | Asynchronous(A) Section |
| 3/12/25 | Paper-6 CAN WE TALK MODELS INTO SEEINGTHE WORLD DIFFERENTLY?
[Presentation PDF]
[Video of Presentation] | Group 10 - Mehrab Mehdi Islam, Michael Miller, Michael Ishak, Lam Nguyen,Robinson Vasquez Ferrer | |
| 3/17/25 | Spring Break | | |
| 3/19/25 | Spring Break | | |
| 3/24/25 | Student Project Presentation Updates-1 | | |
| 3/26/25 | Student Project Presentation Updates-1 | | |
| 3/31/25 | Paper-7 SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples
[Presentation PDF]
[Video of Presentation]
| Group 8 - Ashmal Vayani,Animesh Gupta,Vishal Narnaware,Jay Parmar
| |
| 4/2/25 | Paper-9 Learning to Forget in Text-to-Image Diffusion Models
[Presentation PDF]
[Video of Presentation] | Group 7 - Nakul Rathore,Subhajit Maity, Jaiminkumar Ashokbhai Bhoi, Srinivas Venkatanarayanan | |
| 4/7/25 | Paper-10 Open-set Bias Detection in Text-to-Image Generative Models
[Presentation PDF]
[Video of Presentation] | Group 12 - Umaima Khan(A), Karthika, Sabab, Jamal Mapp (A) | |
| 4/9/25 | Paper-11 Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models
[Presentation PDF]
[Video of Presentation]
Paper-8 SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation
[Presentation PDF]
[Video of Presentation] | Group 6 - John Benjamin,Adam Sachs,Zena Himes,Asher Gibson
Group 11 - Jihwan Song,Jaden Barnwell,Alejandro Fuste,Zonglin Lyu, Megan Delhi | |
| 4/14/25 | Student Project Presentation Updates-2 | | |
| 4/16/25 | Student Project Presentation Updates-2 | | |
| 4/21/25 | Paper-12 Private Attribute Inference from Images with Vision-Language Models
[Presentation PDF]
[Video of Presentation] | Group 2 - Anirudh Thatipelli, Avinash Reddy, Hafijur Raman, Kyle Cochran | |
| 4/23/25 | Final Exam (Project Paper Due) | | |
| Potential Papers | Hallucination | | |
| | | |
| Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding | | |
| HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data | | |
| Evaluation | | |
| MLLMGUARD:A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models | | |
| MULTITRUST: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models | | |
| Bias | | |
| MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models | | |
| CAN WE TALK MODELS INTO SEEINGTHE WORLD DIFFERENTLY? | | |
| SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples | | |
| Learning to Forget in Text-to-Image Diffusion Models | | |
| Open-set Bias Detection in Text-to-Image Generative Models | | |
| Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models | | |
| Privacy | | |
| Private Attribute Inference from Images with Vision-Language Models | | |
| SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation | | |
| | | |
| Groups | | |
| Group Id | Names | |
| 1 | Qingyang Liu, Inad Alqurashi, Sabbir Mollah, Ahnaf Munir, Saurabh Aggarwal | |
| 2 | Anirudh Thatipelli, Avinash Reddy, Hafijur Raman, Kyle Cochran | |
| 3 | Eduardo Bourget, Nathan Couch, Isaac Tuckey, Rodrigo Vena | |
| 4 | Adam Bawatneh, Zengyan Wang, Scott Spicer, Colin Houde (A) | |
| 5 | Kim, Fazil, Arman Sayan | |
| 6 | John Benjamin,Adam Sachs,Zena Himes,Asher Gibson | |
| 7 | Nakul Rathore,Subhajit Maity, Jaiminkumar Ashokbhai Bhoi, Srinivas Venkatanarayanan | |
| 8 | Ashmal Vayani,Animesh Gupta,Vishal Narnaware,Jay Parmar | |
| 9 | Robert Martin,Judd Brock-Edgar,Jacob Braun,Cameron Nichols,Taylor Tiedge | Asynchronous(A) Section |
| 10 | Mehrab Mehdi Islam, Michael Miller, Michael Ishak, Lam Nguyen,Robinson Vasquez Ferrer | |
| 11 | Jihwan Song,Jaden Barnwell,Alejandro Fuste,Zonglin Lyu, Megan Delhi | |
| 12 | Umaima Khan(A), Karthika, Sabab, Jamal Mapp (A) | |
| | | |