30 citations · 42 across the 16 of their papers we have counts for
7 papers · 1 filter
Exploring MLLM-Diffusion Information Transfer with MetaCanvas
Han Lin, Xichen Pan, Ziqi Huang +10
Multimodal learning has rapidly advanced visual understanding, largely via multimodal large language models (MLLMs) that use powerful LLMs as cognitive cores. In visual generation,…
PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation
Yuanhao Cai, Kunpeng Li, Menglin Jia +11
Recent advances in text-to-video (T2V) generation have achieved good visual quality, yet synthesizing videos that faithfully follow physical laws remains an open challenge. Existin…
StreamDiT: Real-Time Streaming Text-to-Video Generation
Akio Kodaira, Tingbo Hou, Ji Hou +4
Recently, great progress has been achieved in text-to-video (T2V) generation by scaling transformer-based diffusion models to billions of parameters, which can generate high-qualit…
Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models
Xu Ma, Peize Sun, Haoyu Ma +22
Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models.…
Transfer between Modalities with MetaQueries
Xichen Pan, Satya Narayan Shukla, Aashu Singh +9
Unified multimodal models aim to integrate understanding (text output) and generation (pixel output), but aligning these different modalities within a single architecture often dem…
MoCha: Towards Movie-Grade Talking Character Synthesis
Cong Wei, Bo Sun, Haoyu Ma +10
Recent advancements in video generation have achieved impressive motion realism, yet they often overlook character-driven storytelling, a crucial task for automated film, animation…
Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts
Feng Liang, Haoyu Ma, Zecheng He +10
Video personalization, which generates customized videos using reference images, has gained significant attention. However, prior methods typically focus on single-concept personal…