GN

Graham Neubig

0000-0002-2072-3789

cs.CLcs.LGcs.AIcs.SEcs.CVstat.MLcs.PLcs.DLcs.IRcs.SD

On Valency

published · living versions

T-DIG: Text-Conditioned Diversity for Image Generation

with Simran Khanuja, Rohit Gandikota, Gaurav Parmar

1 version

W_sfqntcauv1 · current

Preprints & journals

386 papers in the corpus · 2015–2026

T-DIG: Text-Conditioned Diversity for Image Generation

Simran Khanuja, Rohit Gandikota, Gaurav Parmar et al.

0 citations

2610.29003v12026arXiv

Into the Unknown: Benchmarking AI agents on open scientific research problems

Seungone Kim, Jiayi Geng, Young-Jun Lee et al.

0 citations

2610.19159v12026arXiv

Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking

Parinthapat Pengpun, Simran Khanuja, Graham Neubig

0 citations

2609.10745v12026arXiv

Efficient Test-Time Adaptation through Human-AI Interaction

Zora Zhiruo Wang, Apurva Gandhi, Rulin Shao et al.

0 citations

2609.04141v12026arXiv

Humans are Missing from AI Coding Agent Research

Zora Z. Wang, John Yang, Kilian Lieret et al.

0 citations

2608.12355v12026arXiv

Decomposer: Learning to Decompile Symbolic Music to Programs

Yewon Kim, Apurva Gandhi, David Chung et al.

0 citations

2607.01849v12026arXiv

PACE: A Proxy for Agentic Capability Evaluation

Yueqi Song, Lintang Sutawika, Jiarui Liu et al.

0 citations

2607.02032v22026arXiv

PPT-Eval: A Benchmark for Computer-Use Agents on PowerPoint Tasks

Apurva Gandhi, Vishwas Suryanarayanan, Raja Hasnain Anwar et al.

0 citations

2606.31154v12026arXiv

Discretizing Reward Models

Vijay Viswanathan, Shiqi Wang, Devamanyu Hazarika et al.

0 citations

2606.21795v12026arXiv

Low-Latency Real-Time Audio Game Commentary System via LLM-Based Parallel Text Generation

Ryota Kawamatsu, Anum Afzal, Yuki Saito et al.

0 citations

2606.13322v12026arXiv

Enhancing Software Engineering Through Closed-Loop Memory Optimization

Xuehang Guo, Xingyao Wang, Zora Zhiruo Wang et al.

0 citations

2606.05646v22026arXiv

On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists

Seungone Kim, Dongkeun Yoon, Kiril Gashteovski et al.

1 citation

2605.20668v12026arXiv

Reinforcing Human Behavior Simulation via Verbal Feedback

Weiwei Sun, Xuhui Zhou, Jiarui Liu et al.

0 citations

2605.20506v12026arXiv

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs

Guijin Son, Seungone Kim, Catherine Arnett et al.

0 citations

2605.09063v42026arXiv

Recursive Agent Optimization

Apurva Gandhi, Satyaki Chakraborty, Xiangjun Wang et al.

0 citations

2605.06639v22026arXiv

What do Language Models Learn and When? The Implicit Curriculum Hypothesis

Emmy Liu, Kaiser Sun, Millicent Li et al.

0 citations

2604.08510v12026arXiv

Gym-Anything: Turn any Software into an Agent Environment

Pranjal Aggarwal, Graham Neubig, Sean Welleck

0 citations

2604.06126v12026arXiv

IDIOLEX: Unified and Continuous Representations for Idiolectal and Stylistic Variation

Anjali Kantharuban, Aarohi Srivastava, Fahim Faisal et al.

0 citations

2604.04704v12026arXiv

Effective Strategies for Asynchronous Software Engineering Agents

Jiayi Geng, Graham Neubig

0 citations

2603.21489v22026arXiv

Reasoning over mathematical objects: on-policy reward modeling and test time aggregation

Pranjal Aggarwal, Marjan Ghazvininejad, Seungone Kim et al.

0 citations

2603.18886v12026arXiv

Mind the Sim2Real Gap in User Simulation for Agentic Tasks

Xuhui Zhou, Weiwei Sun, Qianou Ma et al.

0 citations

2603.11245v22026arXiv

A Rubric-Supervised Critic from Sparse Real-World Outcomes

Xingyao Wang, Valerie Chen, Heng Ji et al.

0 citations

2603.03800v12026arXiv

Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches

Anum Afzal, Yuki Saito, Hiroya Takamura et al.

1 citation

2603.02655v22026arXiv

How Well Does Agent Development Reflect Real-World Work?

Zora Zhiruo Wang, Sanidhya Vijayvargiya, Aspen Chen et al.

1 citation

2603.01203v22026arXiv

Modeling Distinct Human Interaction in Web Agents

Faria Huq, Zora Zhiruo Wang, Zhanqiu Guo et al.

0 citations

2602.17588v42026arXiv

Hybrid-Gym: Training Coding Agents to Generalize Across Tasks

Yiqing Xie, Emmy Liu, Gaokai Zhang et al.

0 citations

2602.16819v12026arXiv

Synthesizing scientific literature with retrieval-augmented language models.

Asai, Akari, He, Jacqueline, Shao, Rulin et al.

34 citations

416394462026Nature. 2026;650(8103):857-863

NEMO: Execution-Aware Optimization Modeling via Autonomous Coding Agents

Yang Song, Anoushka Vyas, Zirui Wei et al.

0 citations

2601.21372v32026arXiv

Training Versatile Coding Agents in Synthetic Environments

Yiqi Zhu, Apurva Gandhi, Graham Neubig

0 citations

2512.12216v22025arXiv

ClusterFusion: Hybrid Clustering with Embedding Guidance and LLM Adaptation

Yiming Xu, Yuan Yuan, Vijay Viswanathan et al.

0 citations

2512.04350v22025arXiv

Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities

Fan Yang, Quanting Xie, Atsunori Moteki et al.

0 citations

2511.14945v22025arXiv

EDIT-Bench: Evaluating LLM Abilities to Perform Real-World Instructed Code Edits

Wayne Chi, Valerie Chen, Ryan Shar et al.

0 citations

2511.04486v22025arXiv

The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents

Xingyao Wang, Simon Rosenberg, Juan Michelini et al.

0 citations

2511.03690v22025arXiv

Training Proactive and Personalized LLM Agents

Weiwei Sun, Xuhui Zhou, Weihua Du et al.

1 citation

2511.02208v22025arXiv

How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations

Zora Zhiruo Wang, Yijia Shao, Omar Shaikh et al.

1 citation

2510.22780v22025arXiv

Prompt-MII: Meta-Learning Instruction Induction for LLMs

Emily Xiao, Yixiao Zeng, Ada Chen et al.

0 citations

2510.16932v22025arXiv

MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linking

Sathyanarayanan Ramamoorthy, Vishwa Shah, Simran Khanuja et al.

1 citation

2510.14307v12025arXiv

Grounding Multilingual Multimodal LLMs With Cultural Knowledge

Jean de Dieu Nyandwi, Yueqi Song, Simran Khanuja et al.

2 citations

2508.07414v22025arXiv

Checklists Are Better Than Reward Models For Aligning Language Models

Vijay Viswanathan, Yanchao Sun, Shuang Ma et al.

1 citation

2507.18624v22025arXiv

Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows

Valerie Chen, Ameet Talwalkar, Robert Brennan et al.

5 citations

2507.08149v22025arXiv

OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety

Sanidhya Vijayvargiya, Aditya Bharat Soni, Xuhui Zhou et al.

0 citations

2507.06134v22025arXiv

Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning

Maggie Huan, Yuetai Li, Tuney Zheng et al.

1 citation

2507.00432v22025arXiv

CAIRe: Cultural Attribution of Images by Retrieval-Augmented Evaluation

Arnav Yayavaram, Siddharth Yayavaram, Simran Khanuja et al.

0 citations

2506.09109v22025arXiv

Go-Browse: Training Web Agents with Structured Exploration

Apurva Gandhi, Graham Neubig

0 citations

2506.03533v22025arXiv

Coding Agents with Multimodal Browsing are Generalist Problem Solvers

Aditya Bharat Soni, Boxuan Li, Xingyao Wang et al.

0 citations

2506.03011v12025arXiv

BehaviorBox: Automated Discovery of Fine-Grained Performance Differences Between Language Models

Lindia Tjuatja, Graham Neubig

0 citations

2506.02204v22025arXiv

The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think

Seongyun Lee, Seungone Kim, Minju Seo et al.

0 citations

2505.10185v12025arXiv

VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge

Yueqi Song, Tianyue Ou, Yibo Kong et al.

0 citations

2504.10342v32025arXiv

Do LLMs Understand Your Translations? Evaluating Paragraph-level MT with Question Answering

Patrick Fernandes, Sweta Agrawal, Emmanouil Zaranis et al.

0 citations

2504.07583v32025arXiv

Inducing Programmatic Skills for Agentic Tasks

Zora Zhiruo Wang, Apurva Gandhi, Graham Neubig et al.

0 citations

2504.06821v22025arXiv

Career total: 697 works. 386 are in this corpus.Showing the 50 most recent.

Profile built from the corpus for this byline.

697

works

27.7K

citations

96

h-index

Corpus papers per year

Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.