34 citations · 45 across the 13 of their papers we have counts for
7 papers · 1 filter
Failed Reasoning Traces Tell You What Is Fixable (But Not by Reading Them)
Nizar Islah, Istabrak Abbes, Irina Rish +2
When post-trained language models fail on reasoning problems, the common test-time-scaling response is to spend more compute on additional attempts, and the failed traces play no f…
Exploring Quantization for Efficient Pre-Training of Transformer Language Models
Kamran Chitsaz, Quentin Fournier, Gonçalo Mordido +1
The increasing scale of Transformer models has led to an increase in their pre-training computational requirements. While quantization has proven to be effective after pre-training…
Mastering Memory Tasks with World Models
Mohammad Reza Samsami, Artem Zholus, Janarthanan Rajendran +1
Current model-based reinforcement learning (MBRL) agents struggle with long-term dependencies. This limits their ability to effectively solve tasks involving extended time gaps bet…
Replay Buffer with Local Forgetting for Adapting to Local Environment Changes in Deep Model-Based Reinforcement Learning
Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad +2
One of the key behavioral characteristics used in neuroscience to determine whether the subject of study -- be it a rodent or a human -- exhibits model-based learning is effective…
Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods
Yi Wan, Ali Rahimi-Kalahroudi, Janarthanan Rajendran +3
In recent years, a growing number of deep model-based reinforcement learning (RL) methods have been introduced. The interest in deep model-based RL is not surprising, given its man…
TAG: Task-based Accumulated Gradients for Lifelong learning
Pranshu Malviya, Balaraman Ravindran, Sarath Chandar
When an agent encounters a continual stream of new tasks in the lifelong learning setting, it leverages the knowledge it gained from the earlier tasks to help learn the new tasks b…
PatchUp: A Feature-Space Block-Level Regularization Technique for Convolutional Neural Networks
Mojtaba Faramarzi, Mohammad Amini, Akilesh Badrinaaraayanan +2
Large capacity deep learning models are often prone to a high generalization gap when trained with a limited amount of labeled training data. A recent class of methods to address t…