Get started
Author

Chenfu Bao

Observed name: Bao, Chenfu
Observed institutions: Baidu (China), Tsinghua University
OpenAlex ID: A5120724678
Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood
2025 · Lin, Xingyu, Wen, Yilin, et al. · arXiv (Cornell University) · 5
PDF
A Framework for Cost-Effective and Self-Adaptive LLM Shaking and Recovery Mechanism
2024 · Chen, Zhiyu, Li, Yu, et al. · arXiv (Cornell University) · 3
PDF
Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems
2026 · Cui, Yu, Yang, Wuli, et al. · arXiv (Cornell University) · 2
PDF
Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via sequence-level likelihood
2026 · Xingyu Lin, Yilin Wen, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 1
PDF
Rethinking GRPO for Large Reasoning Model Safety Alignment
2026 · Chen, Jiawei, Zhang, Yi, et al. · arXiv (Cornell University)
PDF
Trojan Horse: Automated Repository Poisoning against Coding Agents
2026 · Yang, Xiao, Hou, Jinchang, et al. · arXiv (Cornell University)
PDF
Beyond Natural Images: Rethinking AI-Generated Image Detection in Documents
2026 · Fu, Zhangjie, Yan, Jiazhen, et al. · arXiv (Cornell University)
PDF
Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis
2026 · Association for Computational Linguistics 2026, Bao, Chenfu, et al. · Underline Science Inc.
Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via sequence-level likelihood
2026 · Association for Computational Linguistics 2026, Bao, Chenfu, et al. · Underline Science Inc.
Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis
2026 · Wang Cai, Yilin Wen, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Works count: 10
Citation count: 11
H-index: 2
I10-index:
Year
Topic
Type