Papers by Alexander Ilin
Compositional Generalization in Grounded Language Learning via Induced Model Sparsity (2022.naacl-srw)
Copied to clipboard
| Challenge: | induced model sparsity can help achieve compositional generalization and sample efficiency in grounded language learning problems. |
| Approach: | They propose a model that encourages sparse correlations between words and attributes to find a goal in a language-conditioned navigation problem with disentangled observations. |
| Outcome: | The proposed agent maintains high performance even when learning from a handful of demonstrations. |
Generating Demonstrations for In-Context Compositional Generalization in Grounded Language Learning (2024.emnlp-main)
Copied to clipboard
| Challenge: | In-Context-learning and few-shot prompting are viable methods for compositional output generation but they are sensitive to the choice of support examples. |
| Approach: | They propose a method which generates supports and targets current state of the world and then uses them in-context-learning to solve a query. |
| Outcome: | The proposed agent improves performance on a previously unsolved compositional generalization test without loss of performance in other areas. |
Can docstring reformulation with an LLM improve code generation? (2024.eacl-srw)
Copied to clipboard
| Challenge: | Existing approaches focus on training, fine-tuning or prompting LLMs to generate better outputs given the same input. |
| Approach: | They propose to optimize part of the input, the docstring, via reformulation with an LLM to improve code generation. |
| Outcome: | The proposed methods improve code generation on the original HumanEval benchmark and multiple curated variants on the same input. |
Reader: Model-based language-instructed reinforcement learning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing models of RL are limited and need to be re-trained for every new problem. |
| Approach: | They propose a model-based reinforcement learning approach to tackle the environment Read To Fight Monsters, a grounded policy learning problem. |
| Outcome: | The proposed approach performs better than existing model-free SOTA agents in the read to fight monsters environment and is more sample efficient than existing models. |