16 citations · 40 across the 87 of their papers we have counts for
94 papers
Learning What to Recall: Adaptive Multi-Cue Episodic Memory for World Models
Beomsu Kim, Chieh-Hsin Lai, Bac Nguyen +3
World models predict future observations from current experience and actions, yet prediction can depend on observations seen far in the past. Episodic memory preserves past observa…
Does Uniform Discrete Diffusion Need Time?
Chunsan Hong, Chieh-Hsin Lai, Satoshi Hayakawa +3
Uniform discrete diffusion models (UDMs) commonly use explicit time conditioning, but we find that it can often be unnecessary in practice. In this paper, we first show that the po…
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…
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…
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…
Evaluating Intellectual Property Guardrails of Generative Image Models: A Technical Report
Austin T. Hoag, Apostolos Modas, Yunhao Ba +9
Generative image models are capable of producing images that bear a strong resemblance to, or replicate, recognizable intellectual property (IP). In this technical report, we prese…
TuneJury: An Open Metric for Improving Music Generation Preference Alignment
Yonghyun Kim, Junwon Lee, Haiwen Xia +5
We introduce TuneJury, an open, instance-level pairwise reward model for text-to-music that predicts a music preference score from a text prompt and an audio clip. The released che…
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…
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…
Learning to Route Languages for Multilingual Policy Optimization
Geyang Guo, Hiromi Wakaki, Yuki Mitsufuji +2
Large language models~(LLMs) are trained on heterogeneous multilingual corpora, yet existing policy optimization methods often implicitly restrict each training question to a singl…
Understanding and Accelerating the Training of Masked Diffusion Language Models
Chunsan Hong, Sanghyun Lee, Chieh-Hsin Lai +5
Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models (ARMs) for language modeling. However, MDMs are known to learn substantially more sl…
A Unified View of Score-Based and Drifting Models
Chieh-Hsin Lai, Bac Nguyen, Naoki Murata +5
Drifting models train one-step generators by optimizing a kernel-induced mean-shift discrepancy between the data and model distributions, with Laplace kernels used by default in pr…
Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment
Bac Nguyen, Yuhta Takida, Naoki Murata +4
Slot Attention (SA) with pretrained diffusion models has recently shown promise for object-centric learning (OCL), but suffers from slot entanglement and weak alignment between obj…
Noise Scheduling as Information-Guided Allocation in Diffusion Training
Gabriel Raya, Bac Nguyen, Georgios Batzolis +6
We introduce InfoNoise, an online adaptive noise schedule for diffusion training that reallocates optimization effort toward noise levels where denoising is most informative. Toget…
Summary of The Inaugural Music Source Restoration Challenge
Yongyi Zang, Jiarui Hai, Wanying Ge +5
Music Source Restoration (MSR) aims to recover original, unprocessed instrument stems from professionally mixed and degraded audio, requiring the reversal of both production effect…
GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning
Naoki Murata, Yuhta Takida, Chieh-Hsin Lai +4
Training-data attribution for vision generative models aims to identify which training data influenced a given output. While most methods score individual examples, practitioners o…
PAVAS: Physics-Aware Video-to-Audio Synthesis
Oh Hyun-Bin, Yuhta Takida, Toshimitsu Uesaka +2
Recent advances in Video-to-Audio (V2A) generation have achieved impressive perceptual quality and temporal synchronization, yet most models remain appearance-driven, capturing vis…
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…
MeanFlow Transformers with Representation Autoencoders
Zheyuan Hu, Chieh-Hsin Lai, Ge Wu +2
MeanFlow (MF) is a diffusion-motivated generative model that enables efficient few-step generation by learning long jumps directly from noise to data. In practice, it is often used…
Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion
Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi +2
Masked diffusion models have shown promising performance in generating high-quality samples in a wide range of domains, but accelerating their sampling process remains relatively u…
MCA: Modality Composition Awareness for Robust Composed Multimodal Retrieval
Qiyu Wu, Shuyang Cui, Satoshi Hayakawa +3
Multimodal retrieval, which seeks to retrieve relevant content across modalities such as text or image, supports applications from AI search to contents production. Despite the suc…
Theoretical Refinement of CLIP by Utilizing Linear Structure of Optimal Similarity
Naoki Yoshida, Satoshi Hayakawa, Yuhta Takida +3
In this study, we propose an enhancement to the similarity computation mechanism in multimodal contrastive pretraining frameworks such as CLIP. Prior theoretical research has demon…
SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminator
Yuhta Takida, Satoshi Hayakawa, Takashi Shibuya +6
Deep generative models have made significant advances in generating complex content, yet conditional generation remains a fundamental challenge. Existing conditional generative adv…
The Principles of Diffusion Models
Chieh-Hsin Lai, Yang Song, Dongjun Kim +2
This book presents the core principles that have guided the development of diffusion models, tracing their origins and showing how diverse formulations arise from shared mathematic…