collaborators

23 papers

cs.CL2026

Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence

Xuanle Zhao, Qiushi Sun, Jingyu Xiao +16

While Large Language Models (LLMs) have substantially advanced text-to-code synthesis, many real programming tasks specify intent through visual artifacts such as screenshots, char…

cs.LG2026

Flexible Entropy Control in RLVR with a Gradient-Preserving Perspective

Kun Chen, Peng Shi, Fanfan Liu +4

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a critical method for enhancing the reasoning capabilities of Large Language Models (LLMs). However, continuous…

cs.CV2026

DeepSketcher: Internalizing Visual Manipulation for Multimodal Reasoning

Chi Zhang, Haibo Qiu, Qiming Zhang +3

The "thinking with images" paradigm represents a pivotal shift in the reasoning of Vision Language Models (VLMs), moving from text-dominant chain-of-thought to image-interactive re…

cs.AI2026

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

Lei Chen, Xuanle Zhao, Zhixiong Zeng +4

While reinforcement learning (RL) has proven highly effective for general reasoning in vision-language models, its application to tasks requiring deep understanding of information-…

cs.AI2026

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

Lei Chen, Xuanle Zhao, Zhixiong Zeng +3

Chart reasoning presents unique challenges due to its inherent complexity -- requiring precise numerical comprehension, multi-level visual understanding, and logical inference acro…

cs.CV2026

TreeCUA: Efficiently Scaling GUI Automation with Tree-Structured Verifiable Evolution

Deyang Jiang, Jing Huang, Xuanle Zhao +6

Effectively scaling GUI automation is essential for computer-use agents (CUAs); however, existing work primarily focuses on scaling GUI grounding rather than the more crucial GUI p…