Alert button
Picture for Cheng-Hao Liu

Cheng-Hao Liu

Alert button

Iterated Denoising Energy Matching for Sampling from Boltzmann Densities

Feb 09, 2024
Tara Akhound-Sadegh, Jarrid Rector-Brooks, Avishek Joey Bose, Sarthak Mittal, Pablo Lemos, Cheng-Hao Liu, Marcin Sendera, Siamak Ravanbakhsh, Gauthier Gidel, Yoshua Bengio, Nikolay Malkin, Alexander Tong

Viaarxiv icon

Towards equilibrium molecular conformation generation with GFlowNets

Oct 20, 2023
Alexandra Volokhova, Michał Koziarski, Alex Hernández-García, Cheng-Hao Liu, Santiago Miret, Pablo Lemos, Luca Thiede, Zichao Yan, Alán Aspuru-Guzik, Yoshua Bengio

Viaarxiv icon

Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization

Oct 04, 2023
Dinghuai Zhang, Ricky Tian Qi Chen, Cheng-Hao Liu, Aaron Courville, Yoshua Bengio

Figure 1 for Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization
Figure 2 for Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization
Figure 3 for Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization
Figure 4 for Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization
Viaarxiv icon

SE(3)-Stochastic Flow Matching for Protein Backbone Generation

Oct 03, 2023
Avishek Joey Bose, Tara Akhound-Sadegh, Kilian Fatras, Guillaume Huguet, Jarrid Rector-Brooks, Cheng-Hao Liu, Andrei Cristian Nica, Maksym Korablyov, Michael Bronstein, Alexander Tong

Viaarxiv icon

Thompson sampling for improved exploration in GFlowNets

Jun 30, 2023
Jarrid Rector-Brooks, Kanika Madan, Moksh Jain, Maksym Korablyov, Cheng-Hao Liu, Sarath Chandar, Nikolay Malkin, Yoshua Bengio

Figure 1 for Thompson sampling for improved exploration in GFlowNets
Figure 2 for Thompson sampling for improved exploration in GFlowNets
Figure 3 for Thompson sampling for improved exploration in GFlowNets
Viaarxiv icon

Multi-Fidelity Active Learning with GFlowNets

Jun 20, 2023
Alex Hernandez-Garcia, Nikita Saxena, Moksh Jain, Cheng-Hao Liu, Yoshua Bengio

Figure 1 for Multi-Fidelity Active Learning with GFlowNets
Figure 2 for Multi-Fidelity Active Learning with GFlowNets
Figure 3 for Multi-Fidelity Active Learning with GFlowNets
Figure 4 for Multi-Fidelity Active Learning with GFlowNets
Viaarxiv icon

GFlowNets for AI-Driven Scientific Discovery

Feb 01, 2023
Moksh Jain, Tristan Deleu, Jason Hartford, Cheng-Hao Liu, Alex Hernandez-Garcia, Yoshua Bengio

Figure 1 for GFlowNets for AI-Driven Scientific Discovery
Figure 2 for GFlowNets for AI-Driven Scientific Discovery
Figure 3 for GFlowNets for AI-Driven Scientific Discovery
Figure 4 for GFlowNets for AI-Driven Scientific Discovery
Viaarxiv icon

RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design

Nov 25, 2020
Cheng-Hao Liu, Maksym Korablyov, Stanisław Jastrzębski, Paweł Włodarczyk-Pruszyński, Yoshua Bengio, Marwin H. S. Segler

Figure 1 for RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design
Figure 2 for RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design
Figure 3 for RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design
Figure 4 for RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design
Viaarxiv icon