5 papers
Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
Yiming Ren, Yiran Xu, Zicheng Lin +8
We identify a new dimension for enhancing rollout diversity in Group Relative Policy Optimization (GRPO) for LLMs. While GRPO relies on diverse rollouts, prevailing strategies prim…
From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution
Junjie Wang, Yiming Ren, Haoyang Zhang
This beta technical report asks how reusable experience should be represented so that it can function as effective test-time control and as a substrate for iterative evolution. We…
SIN-Bench: Tracing Native Evidence Chains in Long-Context Multimodal Scientific Interleaved Literature
Yiming Ren, Junjie Wang, Yuxin Meng +11
Evaluating whether multimodal large language models truly understand long-form scientific papers remains challenging: answer-only metrics and synthetic "Needle-In-A-Haystack" tests…
AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning
Yiming Ren, Zhiqiang Lin, Yu Li +8
Controllable captioning is essential for precise multimodal alignment and instruction following, yet existing models often lack fine-grained control and reliable evaluation protoco…
Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning
Chenyu Yang, Xizhou Zhu, Jinguo Zhu +9
Recently, vision model pre-training has evolved from relying on manually annotated datasets to leveraging large-scale, web-crawled image-text data. Despite these advances, there is…