Skip to main content

Aligning Visual Generation With Reward Signals

October 14, 2026
Final Oral Examination for Doctor of Philosophy (Computer Science) Ming Li Monday, October 26, 2026 11:00AM – 12:00PM Teaching Academy, Room TA 0221 Zoom | Meeting ID: 958 1471 4171 Passcode:768955 [Bifold] Dissertation Visual generation systems must follow user intent expressed through prompts, structural controls, editing instructions, and preferences. Optimizing a standard denoising loss alone […]

From Perception to Reasoning: Towards Adaptive Video Intelligence

October 13, 2026
Final Oral Examination for Doctor of Philosophy (Computer Science) Shehreen Azad Friday, October 23, 2026 11:00AM – 12:00PM SPRK 229 (Formerly UCF Global) [Bifold] Dissertation Every day, cameras capture an enormous amount of video, from sports broadcasts and movies to security footage, hospital monitoring, traffic cameras, and personal recordings. Far more video is recorded than […]

From Information Structure to Efficient Adaptation: Principled Foundations for Pretrained Models

October 5, 2026
Final Oral Examination for Doctor of Philosophy (Computer Science) Md Kowsher Friday, October 16, 2026 11:00AM – 12:00PM Zoom [Bifold] Dissertation Adapting large pretrained models has become central to machine learning in language, vision, and multimodal settings. A single model is trained once and then adjusted for many tasks, such as text understanding, question answering, […]

Towards Achieving General Video Understanding

October 29, 2025
Final Oral Examination for Doctor of Philosophy (Computer Science) Rohit Gupta Thursday, October 30, 2025 3:00PM – 4:00PM Global 229 [Bifold] Dissertation Video is now a key medium for learning, communication, and autonomy, so perception systems must recognize fine-grained activities, adapt to new concepts, stay robust under change, and support multiple capabilities. Current methods fall […]

Exploring Segmentation, Detection and Tracking in Videos

October 29, 2025
Final Oral Examination for Doctor of Philosophy (Computer Science) Jyoti Kini Friday, October 31, 2025 2:00PM – 3:00PM Research I, 101A [Bifold] Dissertation Autonomous agents rely on robust segmentation, detection, and tracking to perceive, reason about, and act in dynamic environments. These perception capabilities form the core of intelligent systems, from self-driving vehicles navigating urban […]

Towards Label-Efficient Approaches for Dense Video Tasks

October 13, 2025
Final Oral Examination for Doctor of Philosophy (Computer Science) Akash Kumar Monday, October 13, 2025 2:00PM – 3:00PM [Bifold] Dissertation Deep learning has significantly advanced visual understanding tasks like object detection, tracking, and spatio-temporal grounding, benefiting fields such as autonomous vehicles, surveillance systems, and robotics. While large-scale labeled datasets have been crucial to this success, […]

Advancing AI with Synthetic Data: From Perception to Long-Horizon Agents

September 18, 2025
Dr. Vibhav Vineet Microsoft Research Thursday, September 25, 2025 2:00PM – 3:00PM Global 229 | Zoom Abstract As AI shifts from passive models to active agents, the key bottleneck has become data—its quality, coverage, and controllability. Constructing labeled datasets, whether for per-pixel segmentation or multi-step user interaction, is slow, expensive, and privacy-sensitive. At the same […]

Generalization towards Novel Scenarios: From Algorithms to Applications

July 10, 2025
Mr. Song Wang University of Virginia Thursday, July 17, 2025 2:00PM – 3:00PM R1 101A | Zoom Abstract As machine learning systems are increasingly deployed in dynamic and real-world environments, it is crucial to ensure their ability to generalize beyond the conditions seen during training, such as new data distributions and novel tasks. In this […]