Yuma Ichikawa

According to our database, Yuma Ichikawa authored at least 21 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Signs Beat Floats: Low-Rank Double-Binary Adaptation for On-Device Fine-Tuning.

Yoshihiko Fujisawa, Yuma Ichikawa, Yudai Fujimoto, Akira Sakai, Katsuki Fujisawa

CoRR, May, 2026

EVE-Agent: Evidence-Verifiable Self-Evolving Agents.

Yamato Arai, Yuma Ichikawa

CoRR, May, 2026

OneComp: One-Line Revolution for Generative AI Model Compression.

Yuma Ichikawa, Keiji Kimura, Akihiro Yoshida, Yudai Fujimoto, Hiroki Tokura, Yamato Arai, Yoshiyuki Ishii, Yusei Kawakami, Genki Shikada, Achille Jacquemond, Yoshihiko Fujisawa, Katsuki Fujisawa, Takumi Honda, Akira Sakai

CoRR, March, 2026

Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression.

Akira Sakai, Yuma Ichikawa

CoRR, February, 2026

Thermal Min-Max Games: Unifying Bounded Rationality and Typical-Case Equilibrium.

Yuma Ichikawa

CoRR, February, 2026

2025

More Than Bits: Multi-Envelope Double Binary Factorization for Extreme Quantization.

Yuma Ichikawa, Yoshihiko Fujisawa, Yudai Fujimoto, Akira Sakai, Katsuki Fujisawa

CoRR, December, 2025

PHOTON: Hierarchical Autoregressive Modeling for Lightspeed and Memory-Efficient Language Generation.

Yuma Ichikawa, Naoya Takagi, Takumi Nakagawa, Yuzi Kanazawa, Akira Sakai

CoRR, December, 2025

LPCD: Unified Framework from Layer-Wise to Submodule Quantization.

Yuma Ichikawa, Yudai Fujimoto, Akira Sakai

CoRR, December, 2025

High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator.

Yuma Ichikawa, Shuhei Kashiwamura, Ayaka Sakata

CoRR, October, 2025

Continuous Parallel Relaxation for Finding Diverse Solutions in Combinatorial Optimization Problems.

Yuma Ichikawa, Hiroaki Iwashita

Trans. Mach. Learn. Res., 2025

Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization.

Yamato Arai, Yuma Ichikawa

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Optimization by Parallel Quasi-Quantum Annealing with Gradient-Based Sampling.

Yuma Ichikawa, Yamato Arai

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Statistical Mechanics of Min-Max Problems.

Yuma Ichikawa, Koji Hukushima

Trans. Mach. Learn. Res., 2024

Ratio Divergence Learning Using Target Energy in Restricted Boltzmann Machines: Beyond Kullback-Leibler Divergence Learning.

Yuichi Ishida, Yuma Ichikawa, Aki Dote, Toshiyuki Miyazawa, Koji Hukushima

CoRR, 2024

Training-Free Time-Series Anomaly Detection: Leveraging Image Foundation Models.

Nobuo Namura, Yuma Ichikawa

CoRR, 2024

Continuous Tensor Relaxation for Finding Diverse Solutions in Combinatorial Optimization Problems.

Yuma Ichikawa, Hiroaki Iwashita

CoRR, 2024

Controlling Continuous Relaxation for Combinatorial Optimization.

Yuma Ichikawa

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Adaptive Flip Graph Algorithm for Matrix Multiplication.

Yamato Arai, Yuma Ichikawa, Koji Hukushima

Proceedings of the 2024 International Symposium on Symbolic and Algebraic Computation, 2024

Learning Dynamics in Linear VAE: Posterior Collapse Threshold, Superfluous Latent Space Pitfalls, and Speedup with KL Annealing.

Yuma Ichikawa, Koji Hukushima

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

Dataset Size Dependence of Rate-Distortion Curve and Threshold of Posterior Collapse in Linear VAE.

Yuma Ichikawa, Koji Hukushima

CoRR, 2023

2022

Toward Unlimited Self-Learning Monte Carlo with Annealing Process Using VAE's Implicit Isometricity.

Yuma Ichikawa, Akira Nakagawa, Hiromoto Masayuki, Yuhei Umeda

CoRR, 2022