He, Jiajun

10 publications

NeurIPS 2025 FEAT: Free Energy Estimators with Adaptive Transport Yuanqi Du, Jiajun He, Francisco Vargas, Yuanqing Wang, Carla P Gomes, José Miguel Hernández-Lobato, Eric Vanden-Eijnden

ICLRW 2025 No Trick, No Treat: Pursuits and Challenges Towards Simulation-Free Training of Neural Samplers Jiajun He, Yuanqi Du, Francisco Vargas, Dinghuai Zhang, Shreyas Padhy, RuiKang OuYang, Carla P Gomes, José Miguel Hernández-Lobato

ICML 2025 Progressive Tempering Sampler with Diffusion Severi Rissanen, Ruikang Ouyang, Jiajun He, Wenlin Chen, Markus Heinonen, Arno Solin, José Miguel Hernández-Lobato

ICLRW 2025 Towards Training One-Step Diffusion Models Without Distillation Mingtian Zhang, Jiajun He, Wenlin Chen, Zijing Ou, José Miguel Hernández-Lobato, Bernhard Schölkopf, David Barber

AISTATS 2025 Training Neural Samplers with Reverse Diffusive KL Divergence Jiajun He, Wenlin Chen, Mingtian Zhang, David Barber, José Miguel Hernández-Lobato

NeurIPS 2024 Accelerating Relative Entropy Coding with Space Partitioning Jiajun He, Gergely Flamich, José Miguel Hernández-Lobato

ICMLW 2024 Bidirectional Consistency Models Liangchen Li, Jiajun He

NeurIPSW 2024 Getting Free Bits Back from Rotational Symmetries in LLMs Jiajun He, Gergely Flamich, José Miguel Hernández-Lobato

ICLR 2024 RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations Jiajun He, Gergely Flamich, Zongyu Guo, José Miguel Hernández-Lobato

NeurIPS 2023 Compression with Bayesian Implicit Neural Representations Zongyu Guo, Gergely Flamich, Jiajun He, Zhibo Chen, José Miguel Hernández-Lobato