Egocentric action transfer aims to decouple the semantic action from egocentric observations and reproduce them in new visual contexts, enabling scalable world simulation, embodied policy learning, and robotic data generation. Existing approaches to transferring actions rely on condition-guided video generation, which...
Yue Ma, Peng-Jie Song, Xinyu Wang et al.· 0 citations
Group Relative Policy Optimization (GRPO) has advanced generative model post-training in verifiable domains such as code and mathematics, but evaluating video quality, especially emotional expression, often depends on subjective aesthetics and has no uniquely correct target. Existing approaches typically rely on fixed...
Mingzhe Zheng, Yue Wu, Jing Tan et al.· 0 citations
A central yet under-explored question in Multimodal Large Language Models (MLLMs) is where to connect---how visual information from a hierarchical vision encoder should be wired into the layer-wise semantics of a large language model. Mainstream MLLMs inject a fixed single-layer visual representation into the LLM and t...
Ying-Ying Yan, Jia-Qi Tang, Wei Wei et al.· 0 citations
Spatial audio authoring coordinates source decisions with soundfield synthesis. For editing, plans specify what to change and retain, while reference audio supplies further acoustic detail. We present AMBIT, a unified framework for native First-Order Ambisonics (FOA) generation and editing with three connected contribu...
Kam-Man Wu, Yu Zhang, Peng Fang et al.· 0 citations
Unified audio-video creation requires a single model capable of text-conditioned joint synthesis, bidirectional cross-modal generation, and instruction-guided editing across both modalities. Existing methods rely heavily on paired corpora, which are scarce for joint generation and even rarer for editing. Consequently,...
Kien T. Pham, Yu-Hao Liu, C. Choi et al.· 0 citations
Few-step distillation reduces the sampling cost of diffusion and flow models, but existing approaches often require auxiliary score models or specialized architectures. We show that simple on-policy velocity regression already provides a strong foundation for 4-NFE generation. To represent teacher velocity variation wi...
Jia-Wei Zhang, Zi-Yu Wan, Nan-Ye Ma et al.· 0 citations
WorldSonus, an interactive video-to-audio framework designed for real-time spatial sound synthesis in world models, generalizes effectively to open-domain video-to-audio benchmarks, matching or outperforming state-of-the-art bidirectional models in both acoustic quality and spatial alignment.
Peng Fang, Jing-Yi Fa, Kam-Man Wu et al.· 0 citations
World simulation is inherently multisensory, demanding synchronized visual and acoustic dynamics in real time. Yet prevailing interactive world models remain strictly silent, focusing exclusively on visual rendering and control while overlooking the acoustic dimension. We present HelixWorld, a real-time interactive aud...
Lei Ke, Jia-Hao Pan, Ze-Yue Tian et al.· 0 citations
Advances in generative models have improved video fidelity, enabling long-horizon generation, interactive world modeling, and evolving visual environments. Autoregressive (AR) video generation extends visual sequences through causal rollouts. However, a fundamental bottleneck emerges: as the generated sequence expands,...
Harold Haodong Chen, Rong-Jin Guo, Di-Sen Lan et al.· arXiv.org· 3 citations
USR-Drive is proposed, a unified conditional generative framework that, given only posed multi-view driving videos, jointly recovers dense dynamic geometry and instance-level object layouts within a shared scene representation and delivers state-of-the-art results for both dynamic reconstruction and 3D detection on the...
Li-Heng Chen, Haokai Pang, Cheng Su et al.· 0 citations
It is demonstrated that strengthening the understanding capability of the Boogu-Image system, through a stronger multimodal encoder, agentic prompt rewriting, and related techniques, together with improvements in data quality, training pipelines, and agentic inference-time scaling, can substantially enhance generation...
Guoxuan Chen, Chufeng Xiao, Haoran Yang et al.· arXiv.org· 3 citations
This work proposes IQA-T1, a tool-based visual evidence reasoning framework that augments MLLM reasoning with explicit perceptual observations and constructs Q-Tool, a dataset containing 11k multimodal reasoning chains grounded in tool-generated evidence.