Yuheng Ji (冀昱衡)

My name is Yuheng Ji, a lyric poet, a passionate lover of life and a master student at degree Chinese Academy of Science, Institute of Automation (CASIA). I'm supervised by Prof. Xiaolong Zheng. My research interests include vision-language models and embodied AI.

Email  /  Google Scholar  /  Poetry Anthology

My research interests primarily lie in embodied AI and computer vision.
* denotes equal contributions.

We developed Reason-RFT, a novel reinforcement fine-tuning framework that enhances visual reasoning capabilities in Vision-Language Models (VLMs). Reason-RFT employs a two-phase training strategy: (1) Supervised Fine-Tuning (SFT) with curated Chain-of-Thought (CoT) data to activate reasoning potential, followed by (2) Group Relative Policy Optimization (GRPO)-based reinforcement learning to generate diverse reasoning-response pairs.

We developed RoboBrain, an MLLM-based model that combines robotic and general multi-modal data, utilizes a multi-stage training strategy, and incorporates long videos and high-resolution images to improve its robotic manipulation capabilities. Extensive experiments demonstrate that RoboBrain achieves state-of-the-art performance across various robotic tasks, highlighting its potential to advance robotic brain capabilities.

This work introduces Multi-Sensor Corruption Benchmark (MSC-Bench), the first comprehensive benchmark aimed at evaluating the robustness of multi-sensor autonomous driving perception models against various sensor corruptions.

Spatiotemporal Graph Learning (SGL) under Zero-Inflated Distribution (ZID) is vital for urban risk management but is susceptible to adversarial attacks. Traditional adversarial training (AT) increases performance disparities between classes. We propose the MinGRE framework to reduce these disparities and enhance robustness, promoting more equitable and robust models.

We propose a parameter-efficient adversarial adaptation method named AdvLoRA by low-rank adaptation to improve the robustness of vision-language models.

We propose a cross-modal hashing framework called CCMH (CLIP-based Cross-Modal Hashing), which facilitates the transferability of a well-trained real-value semantic subspace to a hash semantic subspace.

在攻读硕博期间参与了以下项目研究，主要负责项目中跨模态信息语义融合与理解等专题研究工作：