Mengzhang Cai
4 papers · 2025–2026 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
chain-of-thought reasoning
(2)
policy optimization
(1)
mathematical reasoning
(1)
language model
(1)
data selection
(1)
vision-language model
(1)
chart reasoning
(1)
large language model
(1)
data optimization
(1)
closed-loop learning
(1)
analogical problem-solving
(1)
reasoning transfer
(1)
token-level entropy
(1)
reinforcement learning
(1)
programmatic synthesis
(1)
Papers
ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch
ACL 2026
Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token’s Nature
ACL 2026
MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer
EMNLP 2025
Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning
EMNLP 2025