Koichi Saito

5 papers · 2023–2026 · 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 (12)

Venues

CVPR (1) ICLR (1) ICML (1) NAACL (1) NeurIPS (1)

Top co-authors

Yuki Mitsufuji (4) Yuhta Takida (2) Zhi Zhong (2) Chris Donahue (2) Chieh-Hsin Lai (2) Shinji Watanabe (2) Takashi Shibuya (2) Shuyang Cui (1) Jia Qi Yip (1) Jinchuan Tian (1)

Research topics

Artificial Intelligence (3) Machine Learning (3) Core AI (3) Deep Learning (2) Models (2) Optimization & Theory (2) Computer Vision (1) Speech & Audio (1) Application Areas (1) Learning Types (1) Processing (1) Synthesis (1)

Keywords

diffusion model (2) knowledge distillation (1) speech synthesis (1) speech recognition (1) posterior sampling (1) speech enhancement (1) gibbs sampler (1) inverse problem (1) consistency model (1) classifier-free guidance (1) evaluation metric (1) length generalization (1) multimodal alignment (1) one-step generation (1) blind restoration (1) preference data (1) music generation (1) linear operator (1) speech evaluation (1) audio coding (1)

Papers

Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models CVPR 2026 Music Arena: Live Evaluation for Text-to-Music NeurIPS 2025 SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation ICLR 2025 VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music NAACL 2025 GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration ICML 2023