News

We are very happy to welcome a new MCL member, Yijin Chen. Here is a quick interview with Yijin:

1. Could you briefly introduce yourself and your research interests?

My name is Yijin Chen. I joined MCL this summer. My main research interest is image recognition based on Green Learning, building mathematically interpretable visual recognition algorithms that can surpass the performance of deep networks without relying on backpropagation. Before joining MCL, I mainly focused on applications of artificial intelligence, as well as some work related to hardware, such as embedded systems and FPGA.

2. What is your impression of MCL and USC?

My first impression of MCL is that it is a very principled lab. Its emphasis on mathematical clarity, reproducible hard metrics, and the requirement that every module can be explained from beginning to end is very different from the “tune until it works” atmosphere I had encountered before. The USC campus itself is also beautiful, and the school’s culture is very appealing. I feel extremely proud to become a member of MCL and of USC.

3. What is your future expectation and plan in MCL?

MCL is a lab that places great emphasis on mathematical thinking, and I hope I can strengthen my own mathematical thinking here. Deep learning and Green Learning are two very different things, and I hope I can approach research on Green Learning from a more rational, more mathematically grounded perspective. We are currently working on advancing Green Learning into its next stage. In the long run, I hope I can make contributions to this work, and grow into a researcher who can explain every design choice from first principles.

Congratulations to Xinyu Wang for passing her defense! Xinyu’s thesis is titled “ Towards Efficient Visual Perception: From Feature Learning to Visual Reasoning.” Here is a brief summary of her thesis:

Visual perception serves as a fundamental component of modern computer vision, enabling the interpretation of large-scale image and video data. As visual data continues to grow in complexity, there is an increasing demand for efficient and scalable frameworks that bridge low-level representations and high-level understanding. This dissertation addresses this challenge by exploring a unified trajectory of efficient visual perception, evolving from feature learning to spatio-temporal modeling and ultimately to scene-conditioned visual reasoning. This dissertation first introduces a statistics-based feature generation framework for image classification, built upon the Least-squares Normal Transform, which reformulates classification as a regression problem for efficient feature learning. It generates discriminative and complementary features, boosting decision learning and training convergence with low computational overhead. It then investigates a particularly challenging visual task, video camouflaged object detection. The proposed GreenVCOD is a lightweight framework that captures temporal context through a Temporal Neighborhood prediction cube, enabling implicit motion modeling without additional computational cost. Building upon this, IDM-VCOD introduces a dual-motion design that combines implicit semantic refinement with explicit motion alignment, along with a selective activation mechanism to balance accuracy and efficiency. Finally, this dissertation shifts toward a reasoning-based paradigm for visual perception. Camouflaged object detection is reformulated as a scene-conditioned pattern-deviation reasoning problem. By leveraging background-aware retrieval and prototype-based reasoning, it identifies subtle deviations without relying on pixel-level supervision. Overall, the proposed methods demonstrate that lightweight design, combined with structured statistical modeling and scene-conditioned reasoning, can effectively address challenging visual perception tasks without relying on heavy supervision or large-scale model training.

We would like to congratulate Kevin Yang for receiving his Ph.D. degree during the Viterbi Hooding Ceremony held on May 13, 2026, at the Bovard Auditorium. Here is a brief sharing of his Ph.D. experience at MCL:

My Ph.D. journey at the University of Southern California has been both challenging and rewarding. My dissertation, titled “Interpretable and Efficient Multimodal Data Interplay: Algorithms and Applications,” focuses on developing machine learning methods that better connect and understand information across different modalities, such as text and images. Through this research, I explored ways to improve the interpretability and efficiency of multimodal systems while designing algorithms that better align with human perception and understanding. This experience strengthened my passion for artificial intelligence and its potential to create meaningful real-world impact.

I am deeply grateful to my advisor, Professor C.-C. Jay Kuo, for his continuous guidance, encouragement, and support throughout my Ph.D. journey. His mentorship has profoundly influenced both my research perspective and personal growth. I would also like to sincerely thank my labmates for their collaboration, friendship, and inspiring discussions along the way. The supportive environment in our lab made challenging moments manageable and accomplishments even more meaningful. I am excited to continue this journey by joining LinkedIn as an AI Engineer in June 2026, where I hope to contribute to the development of impactful AI systems and applications. I will always cherish the experiences, lessons, and relationships built during my Ph.D. years.

Our recent work explores how multi-modality memory can improve medical agents for visual question answering. By storing and retrieving useful information from medical images, patient queries, and clinical reports, the agent can better understand complex cases and provide more accurate and context-aware responses. This direction shows the potential of memory-enhanced medical AI systems for supporting medical VQA tasks.

Understanding animal motion behavior is important for understanding how the brain organizes memory, decision-making, and goal-directed action. In our research, we study mouse navigation behavior using the Morris Water Maze (MWM), a widely used behavioral paradigm for investigating spatial learning and memory in rodents. While conventional measures such as escape latency and path length provide useful summaries of performance, they often do not fully capture the rich and dynamic nature of movement during navigation.

Our research focuses on understanding mouse motion behavior at a finer temporal scale. Instead of treating each trial as a single behavioral unit, we examine how navigation strategies evolve within a trial, since mice may shift among exploration, wall-following, scanning, circling, and more direct platform-oriented movement over time. These within-trial changes can offer deeper insight into learning processes, behavioral flexibility, and group differences that may be overlooked by aggregate metrics alone.

To support this goal, we develop an interpretable and lightweight computational framework for analyzing tracked trajectories from behavioral videos. Our approach analyzes motion continuously over time and identifies sub-trajectory-level navigational states. The pipeline first corrects for tracking irregularities through uniform resampling and smoothing, then derives geometry- and kinematics-based descriptors such as curvature, displacement, turning behavior, and target alignment. These features are mapped to human-readable behavioral categories through a hierarchical rule-based inference process, followed by temporal refinement to reduce fragmented or implausible label switching.

This work emphasizes interpretability and practical usability in neuroscience research. By providing point-wise annotations and visually verifiable outputs, the framework enables behavioral phenotyping and hypothesis-driven analysis of strategy transitions and learning dynamics.