5 citations · 6 across the 17 of their papers we have counts for
19 papers
Enhancing Autoregressive Video Generation via Representation Adversarial Distillation
Fangyu Lin, Xingtong Ge, Lunjie Zhu +8
Few-step autoregressive video generation enables efficient streaming synthesis, but errors introduced in early temporal blocks are reused as context and can propagate through subse…
Omni-LiveAvatar: Minute-Level Real-Time Streaming Joint Audio-Video Avatar Generation
Lunjie Zhu, Xingtong Ge, Fangyu Lin +7
Joint audio-video generative models serve as foundation for immersive and interactive digital-human generation. Nevertheless, most existing models rely on bidirectional attention a…
Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model
Senqiao Yang, Kaichen Zhang, Zhaoyang Jia +20
Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning but struggle with simple streaming perception tasks and process…
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
Xinjie Zhang, Peng Zhang, Shicheng Zheng +21
Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack for efficient text-to…
Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models
Yue Han, Chong Li, Zhening Liu +5
Recent 3D generative models can synthesize high-quality geometry but often struggle to reproduce intricate textures from reference images, largely due to the scarcity of large-scal…
Training-Free Image Editing with Visual Context Integration and Concept Alignment
Rui Song, Guo-Hua Wang, Qing-Guo Chen +6
In image editing, it is essential to incorporate a context image to convey the user's precise requirements, such as subject appearance or image style. Existing training-based visua…
Real-Time Human Frontal View Synthesis from a Single Image
Fangyu Lin, Yingdong Hu, Lunjie Zhu +4
Photorealistic human novel view synthesis from a single image is crucial for democratizing immersive 3D telepresence, eliminating the need for complex multi-camera setups. However,…
Token-level Data Selection for Safe LLM Fine-tuning
Yanping Li, Zhening Liu, Zijian Li +2
Fine-tuning large language models (LLMs) on custom datasets has become a standard approach for adapting these models to specific domains and applications. However, recent studies h…
Flash-VAED: Plug-and-Play VAE Decoders for Efficient Video Generation
Lunjie Zhu, Yushi Huang, Xingtong Ge +5
Latent diffusion models have enabled high-quality video synthesis, yet their inference remains costly and time-consuming. As diffusion transformers become increasingly efficient, t…
Mon3tr: Monocular 3D Telepresence with Pre-built Gaussian Avatars as Amortization
Fangyu Lin, Yingdong Hu, Zhening Liu +3
Immersive telepresence aims to transform human interaction in AR/VR applications by enabling lifelike full-body holographic representations for enhanced remote collaboration. Howev…
Spatia: Video Generation with Updatable Spatial Memory
Jinjing Zhao, Fangyun Wei, Zhening Liu +3
Existing video generation models struggle to maintain long-term spatial and temporal consistency due to the dense, high-dimensional nature of video signals. To overcome this limita…
Feed-Forward 3D Gaussian Splatting Compression with Long-Context Modeling
Zhening Liu, Rui Song, Yushi Huang +5
3D Gaussian Splatting (3DGS) has emerged as a revolutionary 3D representation. However, its substantial data size poses a major barrier to widespread adoption. While feed-forward 3…
RemedyGS: Defend 3D Gaussian Splatting against Computation Cost Attacks
Yanping Li, Zhening Liu, Zijian Li +2
As a mainstream technique for 3D reconstruction, 3D Gaussian splatting (3DGS) has been applied in a wide range of applications and services. Recent studies have revealed critical v…
Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference
Cheng Yuan, Zhening Liu, Jiashu Lv +4
With the rapid development of large multimodal models (LMMs), multimodal understanding applications are emerging. As most LMM inference requests originate from edge devices with li…
Dynamics-Aware Gaussian Splatting Streaming Towards Fast On-the-Fly 4D Reconstruction
Zhening Liu, Yingdong Hu, Xinjie Zhang +4
The recent development of 3D Gaussian Splatting (3DGS) has led to great interest in 4D dynamic spatial reconstruction. Existing approaches mainly rely on full-length multi-view vid…
MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenes
Xinjie Zhang, Zhening Liu, Yifan Zhang +7
4D Gaussian Splatting (4DGS) has recently emerged as a promising technique for capturing complex dynamic 3D scenes with high fidelity. It utilizes a 4D Gaussian representation and…
EVA-Gaussian: 3D Gaussian-based Real-time Human Novel View Synthesis under Diverse Multi-view Camera Settings
Yingdong Hu, Zhening Liu, Jiawei Shao +2
Feed-forward based 3D Gaussian Splatting methods have demonstrated exceptional capability in real-time novel view synthesis for human models. However, current approaches are confin…
Bidirectional Stereo Image Compression with Cross-Dimensional Entropy Model
Zhening Liu, Xinjie Zhang, Jiawei Shao +2
With the rapid advancement of stereo vision technologies, stereo image compression has emerged as a crucial field that continues to draw significant attention. Previous approaches…
CAMSIC: Content-aware Masked Image Modeling Transformer for Stereo Image Compression
Xinjie Zhang, Shenyuan Gao, Zhening Liu +6
Existing learning-based stereo image codec adopt sophisticated transformation with simple entropy models derived from single image codecs to encode latent representations. However,…