- 🔭 I’m currently a Ph.D student in SJTU(IWIN Lab), now i am a intern research in Alibaba Cloud(飞天实验室).
- 🌱 I’m currently learning LLM/MLLM, explainable attention, information flow, Truthful AI
- 💬 欢迎大家找我一起做一些有趣的工作,目前比较感兴趣的是幻觉/信息流/空间推理/GRPO/DPO
- 📫 我的邮箱: framebreak@sjtu.edu.cn. 微信:SemiZxf
- 🌱 homepage:(zhangbaijin.github.io)
- 💬 Google sclolar: Google scholar
-
PhD @ SJTU
- Shang Hai
-
10:26
(UTC +08:00) - zhangbaijin.github.io
Pinned Loading
-
From-Redundancy-to-Relevance
From-Redundancy-to-Relevance Public[NAACL 2025 Oral] 🎉 From redundancy to relevance: Enhancing explainability in multimodal large language models
-
FanshuoZeng/Simignore
FanshuoZeng/Simignore Public[AAAI 2025] Code for paper:Enhancing Multimodal Large Language Models Complex Reasoning via Similarity Computation
Python 3
-
SpA-Former-shadow-removal
SpA-Former-shadow-removal Public[IJCNN 2023 Oral]: SpA-Former:An Effective and Lightweight Transformer for Image Shadow Removal
-
-
Awesome-MLLM-Hallucination
Awesome-MLLM-Hallucination PublicForked from showlab/Awesome-MLLM-Hallucination
📖 A curated list of resources dedicated to hallucination of multimodal large language models (MLLM).
-
Awesome-LLM-3D
Awesome-LLM-3D PublicForked from ActiveVisionLab/Awesome-LLM-3D
Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources
If the problem persists, check the GitHub status page or contact support.