1 citations · 1 across the 9 of their papers we have counts for
11 papers
Best-of-Depth: Learning Exploratory Dynamics in Looped Transformers
Shota Takashiro, Takeshi Kojima, Masanori Koyama +2
Looped Transformers extend inference-time computation through repeated latent-state updates, but final-depth training does not directly encourage useful intermediate alternatives.…
Steering Recurrent Reasoners at Inference Time with Readout Feedback
Shunsuke Kamiya, Masanori Koyama, Seongcheol Jeong +5
Recurrent models, which repeatedly update latent states with shared computation blocks, have emerged as powerful architectures for solving complex reasoning tasks. Existing inferen…
Looped Transformers with Source-Centered State Evolution
Bum Jun Kim, Kohei Hayashi, Shunsuke Kamiya +3
Looped Transformers create a useful train- and test-time compute axis by reusing the same Transformer block over recurrent depth, increasing effective depth at a fixed parameter co…
Anti Mode-Collapse in Mean-Field Transformer via Auxiliary Variables
Masaaki Imaizumi, Masanori Koyama, Noboru Isobe +1
We use a mean-field-based transformer model to theoretically investigate how auxiliary variables, such as positional encoding, prevent mode collapse of self-attention mechanisms. T…
C-voting: Confidence-Based Test-Time Voting without Explicit Energy Functions
Kenji Kubo, Shunsuke Kamiya, Masanori Koyama +3
Neural network models with latent recurrent processing, where identical layers are recursively applied to the latent state, have gained attention as promising models for performing…
Exploration of Fast-Slow Latent Recurrence for Train-Short, Test-Long Generalization
Shota Takashiro, Masanori Koyama, Takeru Miyato +3
We study out of distribution generalization in streaming tasks where models are trained on short sequences but must operate over much longer, unknown horizons under bounded memory.…
DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation
Makoto Shing, Masanori Koyama, Takuya Akiba
End-to-end backpropagation requires storing activations throughout all layers, creating memory bottlenecks that limit model scalability. Existing block-wise training methods offer…
Pairwise Optimal Transports for Training All-to-All Flow-Based Condition Transfer Model
Kotaro Ikeda, Masanori Koyama, Jinzhe Zhang +2
In this paper, we propose a flow-based method for learning all-to-all transfer maps among conditional distributions that approximates pairwise optimal transport. The proposed metho…
Inter-environmental world modeling for continuous and compositional dynamics
Kohei Hayashi, Masanori Koyama, Julian Jorge Andrade Guerreiro
Various world model frameworks are being developed today based on autoregressive frameworks that rely on discrete representations of actions and observations, and these frameworks…
Flow matching achieves almost minimax optimal convergence
Kenji Fukumizu, Taiji Suzuki, Noboru Isobe +2
Flow matching (FM) has gained significant attention as a simulation-free generative model. Unlike diffusion models, which are based on stochastic differential equations, FM employs…
Extended Flow Matching: a Method of Conditional Generation with Generalized Continuity Equation
Noboru Isobe, Masanori Koyama, Jinzhe Zhang +2
The task of conditional generation is one of the most important applications of generative models, and numerous methods have been developed to date based on the celebrated flow-bas…