← Search

Ziliang Qiu

2 accepted papers

2026

Where Signals Are Sparse, We Synthesize: Reinforcing Self-Corrective Reasoning in Vision–Language Models via Rollout Augmentation

ICML 2026poster

Self-correction is essential for solving complex reasoning problems in vision–language models (VLMs), yet existing reinforcement learning (RL) methods struggle to learn it. Effective self-correction behaviors emerge only rarely during RL, making learning signals sparse. To address this challenge, we…

Cited by 0SourceScholar
2025

Deep Associations, High Creativity: A Simple yet Effective Metric for Evaluating Large Language Models

EMNLP 2025

The evaluation of LLMs’ creativity represents a crucial research domain, though challenges such as data contamination and costly human assessments often impede progress. Drawing inspiration from human creativity assessment, we propose PACE, asking LLMs to generate Parallel Chains of Associations to