VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding Paper • 2611.08449 • Published 18 days ago • 122
GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling Paper • 2608.29335 • Published Aug 29 • 74
Scaling Properties of Text Conditioning in Visual Generation Paper • 2607.29679 • Published Jul 31 • 31
Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving Paper • 2605.22809 • Published May 21 • 27
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders Paper • 2603.06569 • Published Mar 6 • 113
Beyond Language Modeling: An Exploration of Multimodal Pretraining Paper • 2603.03276 • Published Mar 3 • 106
Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models Paper • 2602.24264 • Published Feb 27 • 14
Enhancing Spatial Understanding in Image Generation via Reward Modeling Paper • 2602.24233 • Published Feb 27 • 56
BitDance: Scaling Autoregressive Generative Models with Binary Tokens Paper • 2602.14041 • Published Mar 13 • 47
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence Paper • 2602.08683 • Published Feb 9 • 52
PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss Paper • 2602.02493 • Published Feb 2 • 47
DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models Paper • 2512.24165 • Published Dec 30, 2025 • 53