Ruqi Zhang
@ruqi-zhang.bsky.social
Assistant Professor@PurdueCS | PhD@Cornell | Probabilistic machine learning, Bayesian deep learning, Sampling, MCMC
Cyclical MCMC is a popular method for sampling from complex multimodal distributions. In our #NeurIPS2024 paper, we extend this approach to discrete distributions with novel designs tailored for discrete variables. Applications include graphic models, energy-based models, and language models.
December 13, 2024 at 9:01 AM
Cyclical MCMC is a popular method for sampling from complex multimodal distributions. In our #NeurIPS2024 paper, we extend this approach to discrete distributions with novel designs tailored for discrete variables. Applications include graphic models, energy-based models, and language models.
Excited to be at #NeurIPS2024 all week! If you'd like to chat about:
- Probabilistic & Bayesian ML/DL
- Sampling & generation in discrete data
- LLM & VLM alignment/safety
- ML PhD opportunities at Purdue
…or anything else, feel free to DM or email me!
- Probabilistic & Bayesian ML/DL
- Sampling & generation in discrete data
- LLM & VLM alignment/safety
- ML PhD opportunities at Purdue
…or anything else, feel free to DM or email me!
December 12, 2024 at 8:32 AM
Excited to be at #NeurIPS2024 all week! If you'd like to chat about:
- Probabilistic & Bayesian ML/DL
- Sampling & generation in discrete data
- LLM & VLM alignment/safety
- ML PhD opportunities at Purdue
…or anything else, feel free to DM or email me!
- Probabilistic & Bayesian ML/DL
- Sampling & generation in discrete data
- LLM & VLM alignment/safety
- ML PhD opportunities at Purdue
…or anything else, feel free to DM or email me!