Lin Ma

Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization

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

STAR: STacked AutoRegressive Scheme for Unified Multimodal Learning

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

DeepSketcher: Internalizing Visual Manipulation for Multimodal Reasoning

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

Counting Hallucinations in Diffusion Models

RIV: RECURSIVE INTROSPECTION MASK DIFFUSION VISION LANGUAGE MODEL

M4V: Multimodal Mamba for Efficient Text-to-Video Generation

UItron: Foundational GUI Agent with Advanced Perception and Planning

GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object Detection

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

VITRIX-CLIPIN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction-Editing Data and Long Captions

VITRIX-UniViTAR: Unified Vision Transformer with Native Resolution

CO-MOT: Boosting End-to-end Transformer-based Multi-Object Tracking via Coopetition Label Assignment and Shadow Sets

FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction

Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization

Integer Scale: A Free Lunch for Faster Fine-grained Quantization of LLMs