Johan Obando-Ceron

Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation

Simplicial Embeddings Improve Sample Efficiency in Actor–Critic Agents

Grounding Computer Use Agents on Human Demonstrations

A Comedy of Estimators: On KL Regularization in RL Training of LLMs

Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models

Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning

Generating Creative Chess Puzzles

Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training

Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning

The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning

Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn

Adaptive Computation Pruning for the Forgetting Transformer

The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks