activity
20242026
collaborators

7 papers

cs.CL2026

FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback

Xueqing Wu, Zihan Xue, Da Yin +4

We present FronTalk, a benchmark for front-end code generation that pioneers the study of a unique interaction dynamic: conversational code generation with multi-modal feedback. In…

cs.CL2026

On Asymmetric Optimization of Reasoning and Perception in Vision-Language Model Post-Training

Xueqing Wu, Yu-Chi Lin, Kai-Wei Chang +1

Post-training has greatly improved reasoning in frontier vision-language models, yet its gains for perception remain comparatively limited, creating a bottleneck for end-to-end vis…

cs.CL2025

LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training

Yiming Wang, Da Yin, Yuedong Cui +8

Digital agents require diverse, large-scale UI trajectories to generalize across real-world tasks, yet collecting such data is prohibitively expensive in both human annotation, inf…

cs.CL2025

Re-ReST: Reflection-Reinforced Self-Training for Language Agents

Zi-Yi Dou, Cheng-Fu Yang, Xueqing Wu +2

Finetuning language agents with reasoning-action trajectories is effective, but obtaining these trajectories from human annotations or stronger models is costly and sometimes impra…

cs.CV2025

VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning

Xueqing Wu, Yuheng Ding, Bingxuan Li +4

The ability of large vision-language models (LVLMs) to critique and correct their reasoning is an essential building block towards their self-improvement. However, a systematic ana…

cs.CL2024

DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation

Xueqing Wu, Rui Zheng, Jingzhen Sha +6

Data analysis is a crucial analytical process to generate in-depth studies and conclusive insights to comprehensively answer a given user query for tabular data. In this work, we a…