collaborators

32 papers

cs.CV2026

Spectral Prior for Reducing Exposure Bias in Diffusion Models

Yuya Kobayashi, Masato Ishii, Yuhta Takida +2

Diffusion models typically suffer from error accumulation during iterative sampling, commonly referred to as exposure bias. We reveal systematic frequency-dependent discrepancies b…

cs.LG2026

From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime

Luca Ambrogioni, Giulio Franzese, Alberto Foresti +7

How should a diffusion model decide which noise levels to train on, and how much? Despite the importance of this choice, current noise schedules are based largely on heuristics or…

cs.LG2026

TILDE: TILt-based Distributional Erasure for Concept Unlearning

Naveen George, Naoki Murata, Yuhta Takida +2

Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment: with rising privacy concerns, copyright disputes, trademark constraints, and saf…

cs.LG2026

Locality-Aware Continual Unlearning for Diffusion Models

Naveen George, Naoki Murata, Yuhta Takida +2

Real-world deployment of text-to-image diffusion models requires continual concept removal as new privacy, copyright, or safety obligations arise over time. Existing unlearning met…

cs.SD2026

Spatio-Temporal Audio Language Modeling for Dynamic Sound Sources

Oh Hyun-Bin, Kazuki Shimada, Yuhta Takida +6

Sound events are entities with semantic identities, locations, and trajectories, but current audio-language models usually reason about clips as global event content. Conversely, s…

cs.CV2026

Efficient Reinforcement for Visual-Textual Thinking with Discrete Diffusion Model

Yoonjeon Kim, Yuhta Takida, Chieh-Hsin Lai +2

RL-based post-training has been widely adopted to enable interleaved visual and textual reasoning in unified multimodal models capable of both text and image generation. However, m…