Shohei Taniguchi
8 papers · 2022–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(24)
🔥
Unstoppable · Bronze
🗃️
Keyword Collector
(54)
Venues
Top co-authors
Research topics
Deep Learning
(6)
Machine Learning
(5)
Optimization & Theory · Machine Learning
(4)
Artificial Intelligence
(3)
Architectures
(3)
Core AI · Artificial Intelligence
(3)
Natural Language Processing
(2)
Learning Types · Machine Learning
(2)
Learning Types · Deep Learning
(2)
Models
(2)
Optimization & Theory · Deep Learning
(2)
Computer Vision
(1)
Applications
(1)
Bayesian & Probabilistic
(1)
Core AI · Computer Vision
(1)
Keywords
large language model
(2)
deep reinforcement learning
(1)
importance weighting
(1)
contrastive learning
(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)
density ratio estimation
(1)
langevin dynamics
(1)
contrastive divergence
(1)
spectral analysis
(1)
amortized inference
(1)
generative model
(1)
stochastic optimization
(1)
Papers
CLIP-like Model as a Foundational Density Ratio Estimator
CVPR 2026
Infinity-MoE: Generalizing Mixture of Experts to Infinite Experts
EACL 2026
Position Encoding with Random Float Sampling Enhances Length Generalization of Transformers
EACL 2026
Residual Koopman Spectral Profiling for Predicting and Preventing Transformer Training Instability
UAI 2026
Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence
ICML 2025
ADOPT: Modified Adam Can Converge with Any β_2 with the Optimal Rate
NeurIPS 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
NeurIPS 2022