17 papers
GeoFix: Geometry Fixing for 4D Consistent Generation
Yeobin Hong, Hyojun Go, Dohun Lee +7
Video diffusion models increasingly serve as priors for 4D generation, but the generated videos often lack geometric consistency. Recent approaches address this through post-traini…
Native Action-Prior Learning from Videos for World Action Models
Zhaochong An, Fei Zhang, Menglin Jia +10
World action models integrate future visual dynamics with robot action prediction, but their scalability remains limited by the need for action-annotated robot trajectories. Observ…
World Action Modeling with Progressive Visual Planning
Fei Zhang, Zhaochong An, Duncan Frost +5
World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visual dynamics and actions from an initial observation and instruc…
In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion
Yikai Wang, Xiao Han, Mengmeng Xu +9
Few-step autoregressive video diffusion generates a long video by splitting the video into temporal chunks and generating chunk-by-chunk, each through a short sequence of denoising…
Generative Embodied Multiple Behavior Control Systems for Human-like Agents
Chongyu Bao, Haokai Yang, Yuhan Wang +3
Building autonomous agents that reproduce human behavior in realistic 3D environments has been a longstanding objective in AI. Cognitive neuroscience commonly believes that human b…
Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models
Jiaang Li, Chengzu Li, Zhaochong An +4
Multimodal Large Language Models (MLLMs) achieve strong performance by integrating visual inputs with the rich priors of pretrained language models. However, they often fail on vis…
MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities
Mingqiao Ye, Zhaochong An, Zhitong Gao +11
Any-to-any models predict any modality from any combination of others within a single network, a formulation used in multimodal vision and vision-language models, and increasingly…
Track2View: 4D-Consistent Camera-Controlled Video Generation via Paired 3D Point Tracks
Feng Qiao, Zhaochong An, Zhexiao Xiong +2
Re-rendering an existing video from a novel camera viewpoint requires the output to follow the prescribed camera trajectory while preserving the appearance and dynamics of the orig…
Stitched Value Model for Diffusion Alignment
Hyojun Go, Hyungjin Chung, Prune Truong +8
For practical use, diffusion- or flow-based generative models must be aligned with task-specific rewards, such as prompt fidelity or aesthetic preference. That alignment is challen…
Revisiting the Perception-Distortion Trade-off with Spatial-Semantic Guided Super-Resolution
Dan Wang, Haiyan Sun, Shan Du +4
Image super-resolution (SR) aims to reconstruct high resolution images with both high perceptual quality and low distortion, but is fundamentally limited by the perception-distorti…
VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward
Zhaochong An, Orest Kupyn, Théo Uscidda +5
Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency either by augmenting th…
VecGlypher: Unified Vector Glyph Generation with Language Models
Xiaoke Huang, Bhavul Gauri, Kam Woh Ng +12
Vector glyphs are the atomic units of digital typography, yet most learning-based pipelines still depend on carefully curated exemplar sheets and raster-to-vector postprocessing, w…
Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning
Chengzu Li, Zanyi Wang, Jiaang Li +9
Vision-Language Models have excelled at textual reasoning, but they often struggle with fine-grained spatial understanding and continuous action planning, failing to simulate the d…
HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming
Haonan Qiu, Shikun Liu, Zijian Zhou +10
High-resolution video generation, while crucial for digital media and film, is computationally bottlenecked by the quadratic complexity of diffusion models, making practical infere…
OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory
Zhaochong An, Menglin Jia, Haonan Qiu +12
Storytelling in real-world videos often unfolds through multiple shots -- discontinuous yet semantically connected clips that together convey a coherent narrative. However, existin…
Scaling Zero-Shot Reference-to-Video Generation
Zijian Zhou, Shikun Liu, Haozhe Liu +14
Reference-to-video (R2V) generation aims to synthesize videos that align with a text prompt while preserving the subject identity from reference images. However, current R2V method…
TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models
Zhiheng Liu, Weiming Ren, Haozhe Liu +22
Unified multimodal models (UMMs) aim to jointly perform multimodal understanding and generation within a single framework. We present TUNA, a native UMM that builds a unified conti…