-
Two papers accepted by CVPR 2025!
In this year’s CVPR conference, our team members have published two papers on vision-language model and domain generalization. Several team members will attend the conference in person and welcome everyone to stop by their posters for discussions. Reference Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the...
-
Seven papers accepted by ICLR 2025!
In this year’s ICLR conference, our team members have published seven papers in diffusion models, foundation models and LLM. Several team members will attend the conference in person and welcome everyone to stop by their posters for discussions. Reference How Do Large Language Models Understand Graph Patterns? A Benchmark for...
-
Eight papers accepted by NeurIPS 2024!
In this year’s NeurIPS conference, our team members have published eight papers, inclduing seven papers in the main track and one paper in the dataset and benchmark track, among which two papers are spotlight papers. Several team members will attend the conference in person and welcome everyone to stop by...
-
Our drug combination work is published in Nature Communications!
Due to low success rates and long cycles of traditional drug development, the clinical tendency is to apply omics techniques to reveal patient-level disease characteristics and individualized responses to treatment. However, the heterogeneous form of data and uneven distribution of targets make drug discovery and precision medicine a non-trivial task....
-
We are hiring!
We are hiring researchers and interns major in machine learning and its applications. If you are interested, please send your CV to dongsli@microsoft.com.
-
Two papers accepted by ECCV 2024!
Two papers are accepted by ECCV 2024, entitled Unified Medical Image Pre-training in Language-Guided Common Semantic Space and Online Video Quality Enhancement with Spatial-Temporal Look-up Tables.
-
Attend AI Agent Summit by Andrew NG
We have been invited to attend AI Agent Summit, hosted by Andrew NG (Founder of DeepLearning.ai), to imagine the future of AI Agent and Agentic workflow.
-
One paper published in Nature Communications!
Behaving efficiently and flexibly is crucial for biological and artificial embodied agents. Behavior is generally classified into two types: habitual (fast but inflexible), and goal-directed (flexible but slow). While these two types of behaviors are typically considered to be managed by two distinct systems in the brain, recent studies have...