LIL Lab ORG

[NeurIPS DB 2025] A gym environment for visual spatial reasoning - knot so simple :)

lilGym RL benchmark

The KiloGram Tangrams dataset

Cornell NLVR and NLVR2 are natural language grounding datasets. Each example shows a visual input and a sentence describing it, and is annotated with the truth-value of the sentence.

Cornell Touchdown natural language navigation and spatial reasoning dataset.

Tools for downloading and analyzing summaries and evaluating summarization systems. https://summari.es/

Cornell Semantic Parsing Framework

Cornell House Agent Learning Environment

No description.

Dynamic Robot Instruction Following

Blocks World -- Simulator, Code, and Models (Misra et al. EMNLP 2017)

Materials for a language modeling class, broadly construed

Cornell Instruction Following Framework

No description.

Cereal Bar is a two-player web game designed for studying language understanding agents in collaborative interactions. This repository contains code for the game, a webapp hosting the game, the agent implementation, and recorded interactions in the game. http://lil.nlp.cornell.edu/cerealbar/

Cornell AMR Semantic Parser (Artzi et al., EMNLP 2015)

No description.

Code for the paper "Simulating Bandit Learning from User Feedback for Extractive Question Answering".

Neural Shift Reduce Parser for CCG Semantic Parsing (Misra and Artzi, EMNLP 2016)

An NLP research and data collection platform.

Code for Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions (Artzi and Zettlemoyer, TACL 2013)

"What is Learned in Visually Grounded Neural Syntax Acquisition", Noriyuki Kojima, Hadar Averbuch-Elor, Alexander Rush and Yoav Artzi (ACL 2020)

Code for the paper "Simple Context Compression: Mean-Pooling and Multi-Ratio Training"

Navigation data used for Chen and Mooney 2011 and Artzi and Zettlemoyer 2013 (including cleaned up oracle data)

No description.

Contains various short notebooks showing how to use DyNet. Created for CS 5740 at Cornell University.

Learning from Feedback with Coupled Comprehension and Generation

No description.

No description.

A human-driven recommendation system for academic readings.

[ACL 2025 Oral] Home for the paper "Retrospective Learning from Interactions"

No description.

Code for RSS2018 paper on the Grounded Semantic Mapping Network

BenchPress: A Standardized Evaluation Suite for Context Compression

No description.

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

No description.

The GeoQuery corpus

No description.

Remote teaching and talk recording setup

No description.

Task website for collecting tangram annotations from MTurk.

Data and code release for "Ad hoc conventions generalize to new referents".

Timeline visualization for ML/LM/NLP conferences (2025-2026)

No description.

Continual learning for instruction following in CerealBar.

No description.

No description.

No description.