1 citations · 1 across the 15 of their papers we have counts for
17 papers
ReaDiT Guidance: Control for Image and Video Generation using Diffusion Transformer Features
Jay Mahajan, Chang Liu, Rauf Makharov +3
We present DiT Readout (ReaDiT) Guidance, a lightweight framework for controlling generation with Diffusion Transformer (DiT) models via their internal feature representations. Rea…
ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding
Xinkui Zhao, Enbo Chen, Yifan Zhang +4
Multimodal agents operating in long-horizon environments must build and continually update multimedia memories to support entity-consistent, temporally grounded reasoning. However,…
Video-QTR: Query-Driven Temporal Reasoning Framework for Lightweight Video Understanding
Xinkui Zhao, Zuxin Wang, Yifan Zhang +6
The rapid development of multimodal large-language models (MLLMs) has significantly expanded the scope of visual language reasoning, enabling unified systems to interpret and descr…
S2D-ALIGN: Shallow-to-Deep Auxiliary Learning for Anatomically-Grounded Radiology Report Generation
Jiechao Gao, Chang Liu, Yuangang Li
Radiology Report Generation (RRG) aims to automatically generate diagnostic reports from radiology images. To achieve this, existing methods have leveraged the powerful cross-modal…
BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration
Zhaoyang Li, Dongjun Qian, Kai Su +6
Diffusion Transformer has shown remarkable abilities in generating high-fidelity videos, delivering visually coherent frames and rich details over extended durations. However, exis…
ScenePainter: Semantically Consistent Perpetual 3D Scene Generation with Concept Relation Alignment
Chong Xia, Shengjun Zhang, Fangfu Liu +3
Perpetual 3D scene generation aims to produce long-range and coherent 3D view sequences, which is applicable for long-term video synthesis and 3D scene reconstruction. Existing met…
PhysiInter: Integrating Physical Mapping for High-Fidelity Human Interaction Generation
Wei Yao, Yunlian Sun, Chang Liu +2
Driven by advancements in motion capture and generative artificial intelligence, leveraging large-scale MoCap datasets to train generative models for synthesizing diverse, realisti…
Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value
Yixian Xu, Shengjie Luo, Liwei Wang +2
Diffusion models have achieved remarkable success in generative modeling. Despite more stable training, the loss of diffusion models is not indicative of absolute data-fitting qual…
DiTPainter: Efficient Video Inpainting with Diffusion Transformers
Xian Wu, Chang Liu
Many existing video inpainting algorithms utilize optical flows to construct the corresponding maps and then propagate pixels from adjacent frames to missing areas by mapping. Desp…
Aquarius: A Family of Industry-Level Video Generation Models for Marketing Scenarios
Huafeng Shi, Jianzhong Liang, Rongchang Xie +3
This report introduces Aquarius, a family of industry-level video generation models for marketing scenarios designed for thousands-xPU clusters and models with hundreds of billions…
VC-LLM: Automated Advertisement Video Creation from Raw Footage using Multi-modal LLMs
Dongjun Qian, Kai Su, Yiming Tan +5
As short videos have risen in popularity, the role of video content in advertising has become increasingly significant. Typically, advertisers record a large amount of raw footage…
UnZipLoRA: Separating Content and Style from a Single Image
Chang Liu, Viraj Shah, Aiyu Cui +1
This paper introduces UnZipLoRA, a method for decomposing an image into its constituent subject and style, represented as two distinct LoRAs (Low-Rank Adaptations). Unlike existing…
Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training
Haicheng Wang, Chen Ju, Weixiong Lin +9
In rapidly evolving field of vision-language models (VLMs), contrastive language-image pre-training (CLIP) has made significant strides, becoming foundation for various downstream…
MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding
Rongchang Xie, Chen Du, Ping Song +1
We introduce MUSE-VL, a Unified Vision-Language Model through Semantic discrete Encoding for multimodal understanding and generation. Recently, the research community has begun exp…
MatchTime: Towards Automatic Soccer Game Commentary Generation
Jiayuan Rao, Haoning Wu, Chang Liu +2
Soccer is a globally popular sport with a vast audience, in this paper, we consider constructing an automatic soccer game commentary model to improve the audiences' viewing experie…
UVMap-ID: A Controllable and Personalized UV Map Generative Model
Weijie Wang, Jichao Zhang, Chang Liu +5
Recently, diffusion models have made significant strides in synthesizing realistic 2D human images based on provided text prompts. Building upon this, researchers have extended 2D…
Attribute-conditioned Layout GAN for Automatic Graphic Design
Jianan Li, Jimei Yang, Jianming Zhang +3
Modeling layout is an important first step for graphic design. Recently, methods for generating graphic layouts have progressed, particularly with Generative Adversarial Networks (…