Zhixiong Zeng

OmniActor: A Generalist GUI and Embodied Agent for 2D&3D Worlds

SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start

Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation

STAGE: Stable and Generalizable GRPO for Autoregressive Image Generation

Chart-R1: Chain-of-Thought Supervision and Reinforcement for Advanced Chart Reasoner

DeepSketcher: Internalizing Visual Manipulation for Multimodal Reasoning

Counting Hallucinations in Diffusion Models

UItron: Foundational GUI Agent with Advanced Perception and Planning

Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy