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

DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

Rulin ShaoAkari AsaiShannon Zejiang ShenPang Wei Koh
2026
ICML 2026

Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form QA tasks via… 

VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition

Tanush YadavMohammadreza SalehiJae Sung ParkRanjay Krishna
2026
CVPR

Videos are unique in their ability to capture actions which transcend multiple frames. Accordingly, for many years action recognition was the quintessential task for video understanding.… 

Cocoa: Co-Planning and Co-Execution with AI Agents

K. FengKevin PuMatt LatzkeJoseph Chee Chang
2026
Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems

As AI agents take on increasingly long-running tasks involving sophisticated planning and execution, there is a corresponding need for novel interaction designs that enable deeper human-agent… 

Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation

Yiren LiuViraj ShahSangho SuhYun Huang
2026
Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems

Early-stage interdisciplinary research ideation is often challenged by limited expert access, uncertainty about what to ask, and the cognitive burden of synthesizing unfamiliar domain perspectives.… 

Language Modeling by Language Models

Junyan ChengPeter ClarkKyle Richardson
2025
NeurIPS

Can we leverage LLMs to model the process of discovering novel language model (LM) architectures? Inspired by real research, we propose a multi-agent LLM approach that simulates the conventional… 

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

Sarah WiegreffeOyvind TafjordYonatan BelinkovAshish Sabharwal
2025
ICLR

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… 

Holistically Evaluating the Environmental Impact of Creating Language Models

Jacob MorrisonClara NaJared FernandezJesse Dodge
2025
ICLR

As the performance of artificial intelligence systems has dramatically increased, so too has the environmental impact of creating these systems. While many model developers release estimates of the… 

On Linear Representations and Pretraining Data Frequency in Language Models

Jack MerulloNoah A. SmithSarah WiegreffeYanai Elazar
2025
ICLR

Pretraining data has a direct impact on the behaviors and quality of language models (LMs), but we only understand the most basic principles of this relationship. While most work focuses on… 

AI Safety Should Prioritize the Future of Work

Sanchaita HazraBodhisattwa Prasad MajumderTuhin Chakrabarty
2025
International Conference on Machine Learning (ICML)

Current efforts in AI safety prioritize filtering harmful content, preventing manipulation of human behavior, and eliminating existential risks in cybersecurity or biosecurity. While pressing, this… 

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

Jiacheng LiuTaylor BlantonYanai ElazarJesse Dodge
2025
ACL 2025 Demo Track

We present OLMoTrace, the first system that traces the outputs of language models back to their full, multi-trillion-token training data in real time. OLMoTrace finds and shows verbatim matches… 

1-10Next