影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
-/100
发表论文3 篇
平均评分
年均产出3.0 篇/年
Xuehai Tang
17
Aligning at the Source: Steering Corrective to the Origins of Harmfulness in LLMs
ICLR 2026Desk Rejected
二作26
Modulating LLM Behavior via Context-Specific Activation Steering
ICLR 2026Rejected
二作20
Resolving the Security-Auditability Dilemma with Auditable Latent Chain-of-Thought
ICLR 2026Desk Rejected
二作