PhD candidate in MMLab@NTU. Prev: Tsinghua @thu-ml, Técnico Lisboa.
Awesome-LLM-Reasoning. From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓
3.6kAwesome-Controllable-Diffusion. Papers and resources on Controllable Generation using Diffusion Models, including ControlNet, DreamBooth, IP-Adapter.
505BokehDiffusion. [SIGGRAPH Asia 2025] Official code for "Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models."
126LLMSymbolicReasoningBench. Synthetic data generation for evaluating LLM symbolic and logic reasoning
23ImageMatchingChallenge2022. CVPR 2022 "Image Matching: Local Features and Beyond" workshop challenge: Silver Medal 🥈
21Sentence-Sentiment-Classification. Bi-LSTM with Attention performs sentence-level sentiment classification on Stanford Sentiment Treebank dataset .
4Generative-Powers-of-Ten. An implementation of "Generative Powers of Ten" using DeepFloyd IF
2Pawpularity. Kaggle Competition Bronze Medal 🥉 (205th out of 3537 teams)
1atfortes.
1Repeat-Buyers-Prediction. Alibaba Cloud | Tianchi Competition: TMALL Repeat Buyers Prediction Top 0.7% Solution
1Bicloin. Management system for a platform of bicycle sharing in urban environment. Distributed Systems course @ Instituto Superior Técnico.
1ControlNet. Let us control diffusion models!
1