profile picture

Ronny Luss

reinforcement learning

text generation

explainable ai

efficiency

relation linking

feature attribution

explainable rl

local explainability

multi-modal model

stable diffusion

self-supervisd rule learning

masked training over logical statements

input attribution

llm bias

perturbation-based explanation

6

presentations

SHORT BIO

Ronny Luss is a Staff Research Scientist at IBM Research AI. Ronny has worked on projects across a multitude of industries and applications including product recommendations, advertising, insurance, and explainability, among others, and has published articles in various machine learning and optimization journals and conferences. His general interests are in machine learning, optimization, and statistics and he has most recently focused on Explainable AI developing local explainability tools for various modalities and applications including natural language processing, images, and reinforcement learning. Ronny received a Ph.D. in Operations Research from Princeton University, an M.S. in Management Science and Engineering from Stanford University, and a B.S.E. in Computer Science from the University of Pennsylvania. Prior to joining IBM, Ronny held postdoctoral positions at Tel Aviv University, U.C. Berkeley, and Inria-Paris.

Presentations

NeuroPrune: A Neuro-inspired Topological Sparse Training Algorithm for Large Language Models

Amit Dhurandhar and 6 other authors

Multi-Level Explanations for Generative Language Models

Lucas Monteiro Paes and 10 other authors

Beyond Visual Augmentation: Investigating Bias in Multi-Modal Text Generation

Fnu Mohbat and 5 other authors

Self-Supervised Rule Learning to Link Text Segments to Relational Elements of Structured Knowledge

Shajith Ikbal and 15 other authors

Local Explanations for Reinforcement Learning

Ronny Luss and 2 other authors

AI Explainability 360: Impact and Design

Vijay Arya and 14 other authors

Stay up to date with the latest Underline news!

Select topic of interest (you can select more than one)

PRESENTATIONS

  • All Presentations
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2025 Underline - All rights reserved