Search Results for author:
Found 13 papers, 7 papers with code
Advancing Seq2seq with Joint Paraphrase Learning
We address the problem of model generalization for sequence to sequence (seq2seq) architectures.
Tools Fail: Detecting Silent Errors in Faulty Tools
Tools have become a mainstay of LLMs, allowing them to retrieve knowledge not in their weights, to perform tasks on the web, and even to control robots.
AgentKit: Structured LLM Reasoning with Dynamic Graphs
The chains of nodes can be designed to explicitly enforce a naturally structured "thought process".
Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots
We present Habitat 3. 0: a simulation platform for studying collaborative human-robot tasks in home environments.
SPRING: Studying the Paper and Reasoning to Play Games
Finally, we show the potential of games as a test bed for LLMs.
Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents
We propose the Plan, Eliminate, and Track (PET) framework.
EXCALIBUR: Encouraging and Evaluating Embodied Exploration
Humans constantly explore and learn about their environment out of curiosity, gather information, and update their models of the world.
Self-Supervised Object Goal Navigation with In-Situ Finetuning
In contrast, our LocCon shows the most robust transfer in the real world among the set of models we compare to, and that the real-world performance of all models can be further improved with self-supervised LocCon in-situ training.
Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue
We provide empirical comparisons of metrics, analysis of three models, and make suggestions for how the field might best progress.
FILM: Following Instructions in Language with Modular Methods
In contrast, we propose a modular method with structured representations that (1) builds a semantic map of the scene and (2) performs exploration with a semantic search policy, to achieve the natural language goal.
TransINT: Embedding Implication Rules in Knowledge Graphs with Isomorphic Intersections of Linear Subspaces
We propose TransINT, a novel and interpretable KG embedding method that isomorphically preserves the implication ordering among relations in the embedding space.
Entity-Enriched Neural Models for Clinical Question Answering
We explore state-of-the-art neural models for question answering on electronic medical records and improve their ability to generalize better on previously unseen (paraphrased) questions at test time.
