Get started
Author

Stefano Soatto

Observed names: Soatto, S., Soatto, Stefano
OpenAlex ID: A5127413119
Cycles of Thought: Measuring LLM Confidence through Stable Explanations
2024 · Becker, Evan, Soatto, Stefano · arXiv (Cornell University) · 46
PDF
Reinforcement-aware Knowledge Distillation for LLM Reasoning
2026 · Zhang, Zhaoyang, Jiang, Shuli, et al. · arXiv (Cornell University) · 35
PDF
Priming: Hybrid State Space Models From Pre-trained Transformers
2026 · Chattopadhyay, Aditya, Nunez, Elvis, et al. · arXiv (Cornell University) · 5
PDF
Stacked Residuals of Dynamic Layers for Time Series Anomaly Detection
2022 · Zancato, L., Achille, A., et al. · arXiv (Cornell University) · 4
PDF
StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns
2026 · Sobal, Vlad, Yang, Shuo, et al. · arXiv (Cornell University) · 3
PDF
Asymmetric Actor-Critic for Multi-turn LLM Agents
2026 · Jiang, Shuli, Zhang, Zhaoyang, et al. · arXiv (Cornell University) · 3
PDF
Higher-order pruning of experts in mixture-of-experts language models
2026 · Tseng, Alex M., Kaul, Prannay, et al. · arXiv (Cornell University) · 2
PDF
Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes
2026 · Tan, Jing, Zhang, Zhaoyang, et al. · arXiv (Cornell University) · 2
PDF
Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models
2026 · Liu, Xiaoze, Ram, Dhananjay, et al. · arXiv (Cornell University) · 1
PDF
DLLG: Dynamic Logit-Level Gating of LLM Experts
2026 · Li, Bingnan, Zhang, Zhaoyang, et al. · arXiv (Cornell University)
PDF
ExecTune: Effective Steering of Black-Box LLMs with Guide Models
2026 · Lingam, Vijay, Golatkar, Aditya, et al. · arXiv (Cornell University)
PDF
Works count: 11
Citation count: 101
H-index: 4
I10-index: 2
Year
Topic
Type