Katerina Fragkiadaki

RobotArena $\infty$: Scalable Robot Benchmarking via Real-to-Sim Translation

Generative 3D Object Particle Dynamics

Training Active Vision Reasoners with Multi-Turn Reinforcement Learning

MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second

Self-Questioning Language Models

Maximizing Confidence Alone Improves Reasoning

TAPIP3D: Tracking Any Point in Persistent 3D Geometry

Grounded Reinforcement Learning for Visual Reasoning

Diffusion Beats Autoregressive in Data-Constrained Settings

Unifying 2D and 3D Vision-Language Understanding

PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

RODIN: Injecting 2D Foundational Features to 3D Vision Language Understanding

VADER: Video Diffusion Alignment via Reward Gradients

Unified Multimodal Discrete Diffusion