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
54.94/100
前 6.5%
全站排名 #4,174
发表论文8 篇
平均评分
年均产出4.0 篇/年
Nicola Cancedda
研究方向
Interpretability · Language Modeling · Machine Learning · Natural Language Processing · Machine Translation
20
Verifying Chain-of-Thought Reasoning via Its Computational Graph
ICLR 2026Oral
通讯12
Hallucination Reduction with CASAL: Contrastive Activation Steering for Amortized Learning
ICLR 2026Poster
35
Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts
ICLR 2026Rejected
三作16
Preserving Ignorance Awareness in LLM Fine-Tuning
ICLR 2026Rejected
三作20
AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
NeurIPS 2025Spotlight
23
LLM Unlearning via Neural Activation Redirection
NeurIPS 2025Poster
20
Robust LLM safeguarding via refusal feature adversarial training
ICLR 2025Poster
通讯7
Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources
ICLR 2025Rejected
三作