Author

Si-Da Li

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Open access Oct 2026

AdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum Learning

While reinforcement learning with verifiable reward (RLVR) enhances reasoning in large language models, its efficacy in long-horizon multimodal tasks remains underexplored. Visual Sudoku puzzles pose a representative challenge, requiring multi-step deductive reasoning over both local constraints and global dependency c...

Si-Da Li, Yuan-Xin Liu, Lin-Li Yao et al. · Conference on Empirical Meth... · 0 citations

#artificial intelligence Preprint Jun 2025

LLM Probability Concentration: How Alignment Shrinks the Generative Horizon

These findings establish BF as a diagnostic for understanding and controlling LLM outputs, clarifying how alignment reduces variability, CoT stabilizes generation, and base models can be steered away from diversity.

Chenghao Yang, Si-Da Li, Ari Holtzman · 24 citations · ⚡4