| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Wed, 11 Jun 2025 16:11:42 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"6849aabe-9e1f"
expires: Mon, 29 Dec 2025 08:47:25 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: D107:2BC55:88834E:995C03:69523DC4
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 08:37:25 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210033-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766997445.221769,VS0,VE202
vary: Accept-Encoding
x-fastly-request-id: 4072d0d29edb9b350b2c5efe58344cc0d191e2be
content-length: 9335
JiashenDu Homepage
Bio
I’m a University student of SIST in ShanghaiTech University. My research interests include Artificial Intelligence, Deep Learning, Computer Vision, 3D human Reconstruction / Generation, LLMs and Embodied AI.
Interests
- Artificial Intelligence
- Deep Learning
- Computer Vision
- Large Language Models
- Embodied AI
Education
-
UCB GLOBE COE Exchange program in Computer Science, 2024
University of California, Berkeley
-
Undergrad in Computer Science, 2022
ShanghaiTech University
-
High school undergrad, 2019
No.2 High school of East China Normal University
Recent Publications
Quickly discover relevant content by filtering publications.
Chengfeng Zhao,
Juze Zhang,
Jiashen Du,
Ziwei Shan,
Junye Wang,
Jingyi Yu,
Jingya Wang,
Lan Xu
(2023).
I’M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions.
In CVPR2024.
Featured Publications
Chengfeng Zhao,
Juze Zhang,
Jiashen Du,
Ziwei Shan,
Junye Wang,
Jingyi Yu,
Jingya Wang,
Lan Xu
November, 2023
In CVPR2024
In this paper, we present I’m-HOI, a monocular scheme to faithfully capture the 3D motions of both the human and object in a novel setting, using a minimal amount of RGB camera and object-mounted Inertial Measurement Unit (IMU).
Selected Projects
Learn a powerful motion prior with diffusion models, and use it to denoise, restore, and imagine better motion!
CS194-280 Advanced LLM Agents project. One open question in the study of Large Language Models (LLMs) is whether they can emulate human ethical reasoning and act as believable proxies for human judgment. To investigate this, we introduce a benchmark dataset comprising 196 real-world ethical dilemmas and expert opinions, each segmented into five structured components. We also collect non-expert human responses for comparison, limited to the Key Factors section due to their brevity. We evaluate multiple frontier LLMs using a composite metric framework based on BLEU, Damerau-Levenshtein distance, TF-IDF cosine similarity, and Universal Sentence Encoder similarity. Metric weights are computed through an inversion-based ranking alignment and pairwise AHP analysis, enabling fine-grained comparison of model outputs to expert responses.
This is a fundamental track project for COMPSCI194-196 LLM Agents and LLM Agents hackathon. We focused on exploring robust and generalizable internal representations of lightweight LLMs and investigating the progression of learned features with linear probes and sparse autoencoders in OthelloGPT. Our experiments reveal that SAEs provide a more robust and disentangled decoding of the features the model is learning, particularly for compositional attributes.
This is a Meta Quest track project for the Stanford XR Hackathon. We focused on recovering human psychological dysfunctions, aiming to provide a comprehensive treatment protocol by designing multiple simple interactive meditation games utilizing the power of Meta Quest3. We build interactive environments from scratch in Unity; users can choose different environments, background music, and meditation guidance in Zen.
Posts
Summary page for CS 184/284A Spring 2025 Course Projects
Jiashen Du
Feb 1, 2025
1 min read
Summary page for CS C280 Spring 2025 Course Projects
Jiashen Du
Feb 1, 2025
1 min read
Contact
- jason_du@berkeley.edu
- 1 ZhongKe Road, Shanghai, Pudong New District 200100
- DM Me
- dujsh2022@shanghaitech.edu.cn