Picture for Ran El-Yaniv

Ran El-Yaniv

Google Research, Technion - Israel Institute of Technology

FFN Fusion: Rethinking Sequential Computation in Large Language Models

Add code
Mar 24, 2025
Viaarxiv icon

Learning on LLM Output Signatures for gray-box LLM Behavior Analysis

Add code
Mar 18, 2025
Viaarxiv icon

No Data, No Optimization: A Lightweight Method To Disrupt Neural Networks With Sign-Flips

Add code
Feb 11, 2025
Viaarxiv icon

Puzzle: Distillation-Based NAS for Inference-Optimized LLMs

Add code
Dec 03, 2024
Figure 1 for Puzzle: Distillation-Based NAS for Inference-Optimized LLMs
Figure 2 for Puzzle: Distillation-Based NAS for Inference-Optimized LLMs
Figure 3 for Puzzle: Distillation-Based NAS for Inference-Optimized LLMs
Figure 4 for Puzzle: Distillation-Based NAS for Inference-Optimized LLMs
Viaarxiv icon

Hierarchical Selective Classification

Add code
May 19, 2024
Viaarxiv icon

A framework for benchmarking class-out-of-distribution detection and its application to ImageNet

Add code
Feb 23, 2023
Viaarxiv icon

What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers

Add code
Feb 23, 2023
Viaarxiv icon

Which models are innately best at uncertainty estimation?

Add code
Jun 05, 2022
Figure 1 for Which models are innately best at uncertainty estimation?
Figure 2 for Which models are innately best at uncertainty estimation?
Figure 3 for Which models are innately best at uncertainty estimation?
Figure 4 for Which models are innately best at uncertainty estimation?
Viaarxiv icon

TransBoost: Improving the Best ImageNet Performance using Deep Transduction

Add code
May 27, 2022
Figure 1 for TransBoost: Improving the Best ImageNet Performance using Deep Transduction
Figure 2 for TransBoost: Improving the Best ImageNet Performance using Deep Transduction
Figure 3 for TransBoost: Improving the Best ImageNet Performance using Deep Transduction
Figure 4 for TransBoost: Improving the Best ImageNet Performance using Deep Transduction
Viaarxiv icon

Disrupting Deep Uncertainty Estimation Without Harming Accuracy

Add code
Oct 26, 2021
Figure 1 for Disrupting Deep Uncertainty Estimation Without Harming Accuracy
Figure 2 for Disrupting Deep Uncertainty Estimation Without Harming Accuracy
Figure 3 for Disrupting Deep Uncertainty Estimation Without Harming Accuracy
Figure 4 for Disrupting Deep Uncertainty Estimation Without Harming Accuracy
Viaarxiv icon