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
65.52/100
前 3.5%
全站排名 #2,240
发表论文11 篇
平均评分
年均产出3.7 篇/年
Francesco Pinto
研究方向
privacy; memorization; uncertainty estimation · selective classification · out-of-domain detection · data-shift generalization · gaussian processes · probabilistic programming · computer vision
17
LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference
ICLR 2026Poster
三作5
Do Role-Playing Agents Practice What They Preach? Belief-Behavior Alignment in LLM-Based Simulations of Human Trust
ICLR 2026Withdrawn
通讯18
On the Diminishing Reliability of Reference-Free Memorization Detection in Modern Diffusion Models
ICLR 2026Withdrawn
三作18
Copyright-Protected Language Generation via Adaptive Model Fusion
ICLR 2025Oral
三作34
SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations
ICLR 2025Poster
二作9
Focus On This, Not That! Steering LLMs with Adaptive Feature Specification
ICML 2025Poster
通讯24
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
ICLR 2025Poster
19
AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
NeurIPS 2025Poster
三作25
Towards Certification of Uncertainty Calibration under Adversarial Attacks
ICLR 2025Poster
二作36
Focus On This, Not That! Steering LLMs With Adaptive Feature Specification
ICLR 2025Rejected
通讯