Picture for Nicolas Heess

Nicolas Heess

Informatics

Faithfulness of LLM Self-Explanations for Commonsense Tasks: Larger Is Better, and Instruction-Tuning Allows Trade-Offs but Not Pareto Dominance

Add code
Mar 17, 2025
Viaarxiv icon

Proc4Gem: Foundation models for physical agency through procedural generation

Add code
Mar 11, 2025
Viaarxiv icon

Learning-Order Autoregressive Models with Application to Molecular Graph Generation

Add code
Mar 07, 2025
Viaarxiv icon

Re-evaluating Open-ended Evaluation of Large Language Models

Add code
Feb 27, 2025
Viaarxiv icon

Preference Optimization as Probabilistic Inference

Add code
Oct 05, 2024
Viaarxiv icon

DemoStart: Demonstration-led auto-curriculum applied to sim-to-real with multi-fingered robots

Add code
Sep 10, 2024
Figure 1 for DemoStart: Demonstration-led auto-curriculum applied to sim-to-real with multi-fingered robots
Figure 2 for DemoStart: Demonstration-led auto-curriculum applied to sim-to-real with multi-fingered robots
Figure 3 for DemoStart: Demonstration-led auto-curriculum applied to sim-to-real with multi-fingered robots
Figure 4 for DemoStart: Demonstration-led auto-curriculum applied to sim-to-real with multi-fingered robots
Viaarxiv icon

A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning

Add code
Jun 04, 2024
Figure 1 for A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning
Figure 2 for A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning
Figure 3 for A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning
Figure 4 for A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning
Viaarxiv icon

Deep Dive into Model-free Reinforcement Learning for Biological and Robotic Systems: Theory and Practice

Add code
May 19, 2024
Figure 1 for Deep Dive into Model-free Reinforcement Learning for Biological and Robotic Systems: Theory and Practice
Figure 2 for Deep Dive into Model-free Reinforcement Learning for Biological and Robotic Systems: Theory and Practice
Figure 3 for Deep Dive into Model-free Reinforcement Learning for Biological and Robotic Systems: Theory and Practice
Viaarxiv icon

Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning

Add code
May 03, 2024
Figure 1 for Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning
Figure 2 for Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning
Figure 3 for Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning
Figure 4 for Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning
Viaarxiv icon

The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models

Add code
Apr 04, 2024
Figure 1 for The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models
Figure 2 for The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models
Figure 3 for The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models
Figure 4 for The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models
Viaarxiv icon