Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

Answer, Assemble, Ace: Understanding How Transformers Answer Multiple Choice Questions

Sarah WiegreffeOyvind TafjordYonatan BelinkovAshish Sabharwal
2024
arXiv

Multiple-choice question answering (MCQA) is a key competence of performant transformer language models that is tested by mainstream benchmarks. However, recent evidence shows that models can have… 

Data-driven Discovery with Large Generative Models

Bodhisattwa Prasad MajumderHarshit SuranaDhruv AgarwalPeter Clark
2024
ICML

With the accumulation of data at an unprecedented rate, its potential to fuel scientific discovery is growing exponentially. This position paper urges the Machine Learning (ML) community to exploit… 

Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills

Kolby NottinghamBodhisattwa Prasad MajumderBhavana DalviRoy Fox
2024
ICML

Large language models (LLMs) have recently been used for sequential decision making in interactive environments. However, leveraging environment reward signals for continual LLM actor improvement is… 

Tell, Don't Show!: Language Guidance Eases Transfer Across Domains in Images and Videos

Tarun KalluriBodhisattwa Prasad MajumderManmohan Chandraker
2024
ICML

We introduce LaGTran, a novel framework that utilizes text supervision to guide robust transfer of discriminative knowledge from labeled source to unlabeled target data with domain gaps. While… 

DiscoveryBench: Towards Data-Driven Discovery with Large Language Models

Bodhisattwa Prasad MajumderHarshit SuranaDhruv AgarwalPeter Clark
2024
arXiv

Can the rapid advances in code generation, function calling, and data analysis using large language models (LLMs) help automate the search and verification of hypotheses purely from a set of… 

Climate sensitivity and relative humidity changes in global storm-resolving model simulations of climate change

T. MerlisKai-Yuan ChengIlai GuendelmanStephan Fueglistaler
2024
Science Advances

The climate simulation frontier of a global storm-resolving model (GSRM; or k-scale model because of its kilometer-scale horizontal resolution) is deployed for climate change simulations. The… 

Probabilistic Emulation of a Global Climate Model with Spherical DYffusion

Salva Rühling CachayBrian HennOliver Watt‐MeyerRose Yu
2024
ICML•ML4ESM

Data-driven deep learning models are on the verge of transforming global weather forecasting. It is an open question if this success can extend to climate modeling, where long inference rollouts and… 

PDDLEGO: Iterative Planning in Textual Environments

Li ZhangPeter JansenTianyi ZhangNiket Tandon
2024
STARSEM

Planning in textual environments have been shown to be a long-standing challenge even for current models. A recent, promising line of work uses LLMs to generate a formal representation of the… 

Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action

Jiasen Lu*Christopher Clark*Sangho Lee*Aniruddha Kembhavi
2024
CVPR

We present Unified-IO 2, the first autoregressive multimodal model that is capable of understanding and generating images, text, audio, and action. To unify different modalities, we tokenize inputs… 

ADaPT: As-Needed Decomposition and Planning with Language Models

Archiki PrasadAlexander KollerMareike HartmannTushar Khot
2024
NAACL Findings

Large Language Models (LLMs) are increasingly being used for interactive decision-making tasks requiring planning and adapting to the environment. Recent works employ LLMs-as-agents in broadly two…