16 citations · 40 across the 87 of their papers we have counts for
31 papers · 1 filter
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…
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…
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…
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…
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…
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…
CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow Map Models
Zheyuan Hu, Chieh-Hsin Lai, Yuki Mitsufuji +1
Flow map models such as Consistency Models (CM) and Mean Flow (MF) enable few-step generation by learning the long jump of the ODE solution of diffusion models, yet training remain…
TITAN-Guide: Taming Inference-Time AligNment for Guided Text-to-Video Diffusion Models
Christian Simon, Masato Ishii, Akio Hayakawa +4
In the recent development of conditional diffusion models still require heavy supervised fine-tuning for performing control on a category of tasks. Training-free conditioning via g…
Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution
Yonghyun Park, Chieh-Hsin Lai, Satoshi Hayakawa +7
While diffusion models excel at image generation, their growing adoption raises critical concerns about copyright issues and model transparency. Existing attribution methods identi…
Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry
Junyoung Seo, Jisang Han, Jaewoo Jung +9
We introduce Vid-CamEdit, a novel framework for video camera trajectory editing, enabling the re-synthesis of monocular videos along user-defined camera paths. This task is challen…
Efficiency without Compromise: CLIP-aided Text-to-Image GANs with Increased Diversity
Yuya Kobayashi, Yuhta Takida, Takashi Shibuya +1
Recently, Generative Adversarial Networks (GANs) have been successfully scaled to billion-scale large text-to-image datasets. However, training such models entails a high training…
Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance
Akio Hayakawa, Masato Ishii, Takashi Shibuya +1
We propose a step-by-step video-to-audio (V2A) generation method that provides finer control over the generation process and more realistic audio synthesis. Inspired by traditional…
Dyadic Mamba: Long-term Dyadic Human Motion Synthesis
Julian Tanke, Takashi Shibuya, Kengo Uchida +2
Generating realistic dyadic human motion from text descriptions presents significant challenges, particularly for extended interactions that exceed typical training sequence length…
Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Image
Anubhav Jain, Yuya Kobayashi, Naoki Murata +6
Watermarking techniques are vital for protecting intellectual property and preventing fraudulent use of media. Most previous watermarking schemes designed for diffusion models embe…
VinaBench: Benchmark for Faithful and Consistent Visual Narratives
Silin Gao, Sheryl Mathew, Li Mi +6
Visual narrative generation transforms textual narratives into sequences of images illustrating the content of the text. However, generating visual narratives that are faithful to…
DUSt3R: Enhancing 3D Reconstruction for Dynamic Scenes
Jisang Han, Honggyu An, Jaewoo Jung +7
In this work, we address the task of 3D reconstruction in dynamic scenes, where object motions frequently degrade the quality of previous 3D pointmap regression methods, such as DU…
HumanGif: Single-View Human Diffusion with Generative Prior
Shoukang Hu, Takuya Narihira, Kazumi Fukuda +3
Previous 3D human creation methods have made significant progress in synthesizing view-consistent and temporally aligned results from sparse-view images or monocular videos. Howeve…
MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
Ho Kei Cheng, Masato Ishii, Akio Hayakawa +3
We propose to synthesize high-quality and synchronized audio, given video and optional text conditions, using a novel multimodal joint training framework MMAudio. In contrast to si…
Rethinking Negative Prompting for Concept Suppression: Unconditional Anchoring and Localized Guidance
Anubhav Jain, Yuya Kobayashi, Takashi Shibuya +4
Text-to-image diffusion models have rapidly transitioned from research prototypes to widely deployed tools. Along with their impressive capabilities, these models can also generate…
Blind Inverse Problem Solving Made Easy by Text-to-Image Latent Diffusion
Michail Dontas, Yutong He, Naoki Murata +3
This paper considers blind inverse image restoration, the task of predicting a target image from a degraded source when the degradation (i.e. the forward operator) is unknown. Exis…
Classifier-Free Guidance inside the Attraction Basin May Cause Memorization
Anubhav Jain, Yuya Kobayashi, Takashi Shibuya +4
Diffusion models are prone to exactly reproduce images from the training data. This exact reproduction of the training data is concerning as it can lead to copyright infringement a…
G2D2: Gradient-Guided Discrete Diffusion for Inverse Problem Solving
Naoki Murata, Chieh-Hsin Lai, Yuhta Takida +4
Recent literature has effectively leveraged diffusion models trained on continuous variables as priors for solving inverse problems. Notably, discrete diffusion models with discret…
GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models
M. Jehanzeb Mirza, Mengjie Zhao, Zhuoyuan Mao +12
In this work, we propose GLOV, which enables Large Language Models (LLMs) to act as implicit optimizers for Vision-Language Models (VLMs) to enhance downstream vision tasks. GLOV p…
Mining Your Own Secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models
Saurav Jha, Shiqi Yang, Masato Ishii +7
Personalized text-to-image diffusion models have grown popular for their ability to efficiently acquire a new concept from user-defined text descriptions and a few images. However,…