AI.info
Zheng Ge
Explore Zheng Ge on AI.info.
- onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction
- PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering
- GEBench: Benchmarking Image Generation Models as GUI Environments
- R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging