22 papers · 1 filter
UniVOE: A Removal-Driven Framework for Interaction-Aware Universal Video Object Editing
Shuzhou Yang, Lanqing Guo, Lingen Li +4
Video object removal and injection are reciprocal editing operations between object-present and object-absent video states, yet they differ substantially in training difficulty. Re…
Scaling Unified Multimodal Models to Long-Horizon Interleaved Generation
Ziqiao Peng, Yutao Cui, Wang Lin +12
Unified multimodal models (UMMs) provide an interface for interleaved text-image generation, where generated visual states can directly inform subsequent reasoning and synthesis. H…
WithEveryone: Unified Planning and Identity Grounding for Group Image Generation
Hengyuan Xu, Qixun Wang, Yiji Cheng +5
Identity-preserving image generation becomes increasingly unreliable when a scene must contain many specified people. Beyond retaining each identity, the model must bind every refe…
Twins: Learn to Predict Unified Representations with Focal Loss
Kaixiong Gong, Xin Cai, Bin Lin +9
Unified multimodal models seek a shared visual token space that supports both multimodal understanding and image generation. Discrete methods unify the interface via a shared codeb…
Think, Plan, Paint: Layout-Aware Reasoning for Controllable Image Generation in Unified Models
Junhao Liu, Jian-Wei Zhang, Tao Huang +3
Unified Multimodal Large Language Models (MLLMs) offer a promising paradigm for unifying visual understanding and generation, yet they still struggle to follow complex spatial inst…
Rosetta: Composable Native Multimodal Pretraining
Xiangyue Liu, Zijian Zhang, Miles Yang +3
Achieving true artificial general intelligence requires foundation models capable of integrating new modalities without forgetting prior knowledge. However, accommodating continuou…
GEAR: Guided End-to-End AutoRegression for Image Synthesis
Bin Lin, Zheyuan Liu, Chenguo Lin +8
Visual generative models are typically trained in two stages. A tokenizer is first trained for reconstruction and then frozen, after which a generator is trained on its discrete in…
TMP: Tree-structured Mixed-policy Pruning for Large-scale Image Generation and Editing
Peizhen Zhang, Yang Li, Xunsong Li +10
Modern image generation model rapidly grows their sizes to meet high-fidelity image synthesis. However, they gradually become unaffordable for their enormous parameter consumption…
CrossFlow: One-Step Generation Across Latent and Pixel Spaces
Xiyuan Wang, Xiao Zhang, Yang Li +4
Most diffusion and flow-matching generators define the prior, probability path, and prediction target in the same representation space. Latent diffusion improves efficiency by movi…
HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers
Guozhen Zhang, Xuerui Qiu, Yutao Cui +11
Holistic visual tokenizers are fundamental to unified multimodal models (UMMs) as they map diverse visual inputs into a unified representation space. In this paper, we present HYDR…
Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation
Shuyuan Tu, Qi Tian, Zihan Yang +9
Current open-source diffusion models struggle to generate stable and synchronized audio-visual content, particularly in scenarios demanding complex semantic reasoning. The root cau…
Stabilizing, Scaling & Enhancing MeanFlow for Large-scale Diffusion Distillation
Xiao He, Yang Li, Peizhen Zhang +3
Diffusion models exhibit remarkable generative capability, but their high latency limits practical deployment. Many studies have attempted to reduce sampling steps to accelerate in…
DiffCap-Bench: A Comprehensive, Challenging, Robust Benchmark for Image Difference Captioning
Yuancheng Wei, Haojie Zhang, Linli Yao +7
Image Difference Captioning (IDC) generates natural language descriptions that precisely identify differences between two images, serving as a key benchmark for fine-grained change…
OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning
Kaihang Pan, Qi Tian, Jianwei Zhang +12
While proprietary systems such as Seedance-2.0 have achieved remarkable success in omni-capable video generation, the academic research community lags far behind: most of its model…
Symbiotic-MoE: Unlocking the Synergy between Generation and Understanding
Xiangyue Liu, Zijian Zhang, Miles Yang +3
Empowering Large Multimodal Models (LMMs) with image generation often leads to catastrophic forgetting in understanding tasks due to severe gradient conflicts. While existing parad…
Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis
Shuang Chen, Quanxin Shou, Hangting Chen +16
Unified multimodal models provide a natural and promising architecture for understanding diverse and complex real-world knowledge while generating high-quality images. However, the…
Manifold-Aware Exploration for Reinforcement Learning in Video Generation
Mingzhe Zheng, Weijie Kong, Yue Wu +9
Group Relative Policy Optimization (GRPO) methods for video generation like FlowGRPO remain far less reliable than their counterparts for language models and images. This gap arise…
HYDRA: Representation Harmonized Tokenization for Multimodal Generation and Understanding
Xuerui Qiu, Yutao Cui, Guozhen Zhang +10
Unified Multimodal Models struggle to bridge the fundamental gap between the abstract representations needed for visual understanding and the detailed primitives required for gener…
UniCom: Unified Multimodal Modeling via Compressed Continuous Semantic Representations
Yaqi Zhao, Wang Lin, Zijian Zhang +5
Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic informa…
DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching
Chang Zou, Changlin Li, Yang Li +7
While diffusion models have achieved great success in the field of video generation, this progress is accompanied by a rapidly escalating computational burden. Among the existing a…
iFSQ: Improving FSQ for Image Generation with 1 Line of Code
Bin Lin, Zongjian Li, Yuwei Niu +9
The field of image generation is currently bifurcated into autoregressive (AR) models operating on discrete tokens and diffusion models utilizing continuous latents. This divide, r…
PanGu-Draw: Advancing Resource-Efficient Text-to-Image Synthesis with Time-Decoupled Training and Reusable Coop-Diffusion
Guansong Lu, Yuanfan Guo, Jianhua Han +7
Current large-scale diffusion models represent a giant leap forward in conditional image synthesis, capable of interpreting diverse cues like text, human poses, and edges. However,…