8 papers
PyVision-RL: Forging Open Agentic Vision Models via RL
Shitian Zhao, Shaoheng Lin, Ming Li +4
Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn reasoning, limiting the benefit…
TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning
Ming Li, Jike Zhong, Shitian Zhao +6
The frontier of visual reasoning is shifting toward models like OpenAI o3, which can intelligently create and operate tools to transform images for problem-solving, also known as t…
Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning
Ming Li, Jike Zhong, Shitian Zhao +4
This paper investigates the role of explicit thinking process in rule-based reinforcement fine-tuning (RFT) for MLLMs. We first propose CLS-RL for MLLM image classification, using…
Symbolic Graphics Programming with Large Language Models
Yamei Chen, Haoquan Zhang, Yangyi Huang +4
Large language models (LLMs) excel at program synthesis, yet their ability to produce symbolic graphics programs (SGPs) that render into precise visual content remains underexplore…
PyVision: Agentic Vision with Dynamic Tooling
Shitian Zhao, Haoquan Zhang, Shaoheng Lin +4
LLMs are increasingly deployed as agents, systems capable of planning, reasoning, and dynamically calling external tools. However, in visual reasoning, prior approaches largely rem…
LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis
Shitian Zhao, Qilong Wu, Xinyue Li +10
We introduce LeX-Art, a comprehensive suite for high-quality text-image synthesis that systematically bridges the gap between prompt expressiveness and text rendering fidelity. Our…