Shohei Taniguchi
6 papers · 2022–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Cross-Pollinator (8) π§ Keyword Pioneer π Conference Polyglot (2) π Interdisciplinary Bridge π£ Hot Topic Early Bird
πΊοΈ
Taxonomy Completionist
(15)
π₯
Unstoppable
(5)
Conferences
EACL (2)
ICML (2)
NIPS (2)
Top co-authors
Keywords
model compression
(1)
stochastic optimization
(1)
deep reinforcement learning
(1)
langevin dynamics
(1)
stochastic gradient descent
(1)
hyperparameter optimization
(1)
metropolis-hastings sampling
(1)
posterior sampling
(1)
neural network optimization
(1)
computational efficiency
(1)
markov chain monte carlo
(1)
gibbs sampling
(1)
random sampling
(1)
contrastive divergence
(1)
amortized inference
(1)
generative model
(1)
learning rate
(1)
latent variable model
(1)
deep boltzmann machine
(1)
convergence guarantee
(1)
Papers
Infinity-MoE: Generalizing Mixture of Experts to Infinite Experts
EACL 2026
Position Encoding with Random Float Sampling Enhances Length Generalization of Transformers
EACL 2026
Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence
ICML 2025
ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate
NIPS 2024
End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization
ICML 2023
Langevin Autoencoders for Learning Deep Latent Variable Models
NIPS 2022