Skip to content
View Yusen-Peng's full-sized avatar
21 followers · 76 following

Achievements

Achievement: Pull SharkAchievement: YOLO

Achievements

Achievement: Pull SharkAchievement: YOLO

Organizations

@YP4AIresearch

Block or report Yusen-Peng

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Yusen-Peng/README.md

I am Yusen Peng, an incoming CSE PhD student at The Ohio State University (OSU), starting in Fall 2026. I am fortunate to have been advised by Dr. Sachin Kumar since my senior year as an undergraduate student at OSU 🌰!

My research interest is primarily multimodal LLMs with a specific focus on efficiency. I am currently working on dynamic image tokenization and adaptive token merging to make vision language models (e.g., LLaVA, QwenVL) more efficient.

Previously, I earned my B.S. in Computer Science and Engineering from The Ohio State University with Summa Cum Laude and Honor Research Distinction. I completed my undergrduate thesis under the supervision of Dr. Alper Yilmaz.

Outside of research, I often do guitar recordings on my Instagram! I also enjoy kpop music from my favorite group - Le Sserafim.

“Act like an angel and dress like crazy.” - Kim Chaewon

Here is my updated CV (March 2026): CV_Yusen_Peng

Pinned Loading

  1. CascadeFormer CascadeFormer Public

    [ICPR 2026] CascadeFormer: A Family of Two-stage Cascading Transformers for Skeleton-based Human Action Recognition

    Python 6 2

  2. CE-Bench CE-Bench Public

    [EMNLP-W 2025] CE-Bench: Towards a Reliable Contrastive Evaluation Benchmark of Interpretability of Sparse Autoencoders

    Jupyter Notebook 3 2

  3. SVD3 SVD3 Public

    [under review] SVD^3: Singular Value Decomposition for Visual Geometry Model Compression

    Python 1

  4. DRIP DRIP Public

    DRIP: Dynamic Patch Pooling for Efficient Visual Instruction Tuning

    Jupyter Notebook 5

  5. CascadeFormer2 CascadeFormer2 Public

    [Undergraduate Thesis] From Representation to Policy: Cascade Finetuning and Verifiable Reward Alignment for Human Action Understanding

    Python

  6. Awesome-Collection-Token-Reduction Awesome-Collection-Token-Reduction Public

    Forked from ZLKong/Awesome-Collection-Token-Reduction

    A collection of token reduction (token pruning, merging, clustering, etc.) techniques for ML/AI