YC

Yishuo Cai

0009-0002-5393-8118

cs.CLcs.CVcs.AIcs.CRcs.LG

On Valency

published · living versions

W_umajp7yy·v1 · currentpublished

When Requirements Interact: Scaling Long-Horizon Coding via Interdependent Specifications

with Minzheng Wang, Liang Zhao, Linghao Zhang, Lei Li +3

1 version

Preprints & journals

6 papers in the corpus · 2024–2026

MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement2610.11959v1 · Xiaomi LLM-Core Team: Zongming Qiao, Ziyue Hua, Zirui Ou et al.2026 · 0 citationsarXiv

What Proves You Wrong: Benchmarking Language Models on Falsifiable Research Ideation2608.22948v1 · Ziyue Wang, Aomufei Yuan, Yiran Yao et al.2026 · 0 citationsarXiv

From Player to Master: Enhancing Test-Time Learning of LLM Agents via Reinforcement Learning over Memory2606.08656v1 · Yishuo Cai, Xingyu Guo, Xuancheng Huang et al.2026 · 0 citationsarXiv

Thinking Without Images: Internalizing Visual Manipulation with On-Policy Self-Distillation2606.08719v1 · Yishuo Cai, Jiahui Liu, Yuanxin Liu et al.2026 · 0 citationsarXiv

Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models2602.02185v2 · Yu Zeng, Wenxuan Huang, Zhen Fang et al.2026 · 0 citationsarXiv

Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks2405.12725v1 · Boheng Li, Yishuo Cai, Haowei Li et al.2024 · 21 citationsarXiv

Career total: 10 works. 6 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.