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
65.55/100
前 3.5%
全站排名 #2,238
发表论文12 篇
平均评分
年均产出4.0 篇/年
Luca Zappella
研究方向
deep learning · Network of introspection · transfer learning · incremental learning · Interpretability · Self-supervised learning · Fairness · Robustness
16
ParaRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language Models
ICLR 2026Oral
通讯17
GenCtrl -- A Formal Controllability Toolkit for Generative Models
ICLR 2026Poster
8
Attention to Mamba: A Recipe for Cross-Architecture Distillation
ICLR 2026Rejected
12
On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study
ICLR 2026Withdrawn
18
Controlling Language and Diffusion Models by Transporting Activations
ICLR 2025Spotlight
8
Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity
ICML 2025Poster
23
LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss
NeurIPS 2025Poster
19
Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution
COLM 2025Poster
37
Evaluating Gender Bias Transfer between Pre-trained and Prompt-Adapted Language Models
ICLR 2025Rejected
11
Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs
ICML 2025Poster
5
Uncovering Intersectional Stereotypes in Humans and Large Language Models
ICLR 2025Withdrawn