7 papers · 1 filter
RIGen: Beyond Action Following with Reciprocal Interaction in Generative Gameplay
Mengfei Li, Yi Zhang, Xingtong Ge +8
Generative gameplay requires more than immediate responses to player actions.Actions should have persistent consequences, while the generated world should act according to its own…
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…
Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation
Xingtong Ge, Yutong Wang, Lunjie Zhu +7
Few-step streaming audio--video generation requires both causal modeling and step distillation, yet standard training recipes face two context-related challenges. Teacher forcing p…
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,…
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…
R-AVST: Empowering Video-LLMs with Fine-Grained Spatio-Temporal Reasoning in Complex Audio-Visual Scenarios
Lu Zhu, Tiantian Geng, Yangye Chen +3
Recently, rapid advancements have been made in multimodal large language models (MLLMs), especially in video understanding tasks. However, current research focuses on simple video…
SalQ-VLM: Fine-Grained Saliency-Guided Quantization for Vision-Language Models
Yufei Xue, Yushi Huang, Jiawei Shao +4
Large language models (LLMs) have demonstrated remarkable capabilities across diverse language tasks, motivating their extension to vision-language models (VLMs) for multimodal und…