影响力指数

-/100

发表论文5 篇

平均评分4.5

年均产出2.5 篇/年

Chao Shang

Researcher@Amazon AWS AI·美国·OpenReview

研究方向

Responsible AI · Natural Language Processing · Graph Neural Networks · Machine Learning

Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate

ICLR 2026Withdrawn

Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation

ICLR 2026Rejected

STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents

ICLR 2026Withdrawn

Aligning to Constraints for Data-Efficient Language Model Customization

ICLR 2025Withdrawn

Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models

ICLR 2025Rejected

合作者 (20)

Yassine Benajiba

Nikolaos Pappas

Devang Kulshreshtha