RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation Paper • 2607.06559 • Published 7 days ago • 91
PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space Paper • 2607.05373 • Published 8 days ago • 61
AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer Paper • 2606.31959 • Published 13 days ago • 10
The Verification Horizon: No Silver Bullet for Coding Agent Rewards Paper • 2606.26300 • Published 20 days ago • 51
LISA: Likelihood Score Alignment for Visual-condition Controllable Generation Paper • 2606.27192 • Published 19 days ago • 13
Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments Paper • 2606.14397 • Published 19 days ago • 18
Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models Paper • 2606.25041 • Published 21 days ago • 115
FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation Paper • 2606.24876 • Published 21 days ago • 24
ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Paper • 2606.19531 • Published 27 days ago • 23
DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects Paper • 2606.15133 • Published Jun 13 • 74
Rethinking the Role of Efficient Attention in Hybrid Architectures Paper • 2606.15378 • Published Jun 13 • 20
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients Paper • 2606.18216 • Published 28 days ago • 63
Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models Paper • 2606.16281 • Published 29 days ago • 34
Direct 3D-Aware Object Insertion via Decomposed Visual Proxies Paper • 2606.06601 • Published Jun 4 • 26
Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning Paper • 2606.04923 • Published Jun 3 • 41