| Inference-Time Intervention: Eliciting Truthful Answers from a Language Model K Li, O Patel, F Viégas, H Pfister, M Wattenberg Conference on Neural Information Processing Systems (NeurIPS), 2023 | 834 | 2023 |
| Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task K Li, AK Hopkins, D Bau, F Viégas, H Pfister, M Wattenberg International Conference on Learning Representations (ICLR), 2022 | 444 | 2022 |
| Pose Recognition with Cascade Transformers K Li, S Wang, X Zhang, Y Xu, W Xu, Z Tu Conference on Computer Vision and Pattern Recognition (CVPR), 2021 | 357 | 2021 |
| Multi-modal Graph Neural Network for Joint Reasoning on Vision and Scene Text D Gao, K Li, R Wang, S Shan, X Chen Conference on Computer Vision and Pattern Recognition (CVPR), 2020 | 164 | 2020 |
| Measuring and Controlling Instruction (In)Stability in Language Model Dialogs K Li, T Liu, N Bashkansky, D Bau, F Viégas, H Pfister, M Wattenberg Conference on Language Modeling (COLM), 2024 | 47* | 2024 |
| Designing a Dashboard for Transparency and Control of Conversational AI Y Chen, A Wu, T DePodesta, C Yeh, K Li, NC Marin, O Patel, J Riecke, ... arXiv preprint arXiv:2406.07882, 2024 | 42 | 2024 |
| An AI-Resilient Text Rendering Technique for Reading and Skimming Documents Z Gu, I Arawjo, K Li, JK Kummerfeld, EL Glassman International Conference of Human-Computer Interaction (CHI), 2024 | 40 | 2024 |
| Do Large Language Models Learn World Models or Just Surface Statistics? K Li The Gradient, 2023 | 14 | 2023 |
| Q-Probe: A Lightweight Approach to Reward Maximization for Language Models K Li, S Jelassi, H Zhang, S Kakade, M Wattenberg, D Brandfonbrener International Conference on Machine Learning (ICML), 2024 | 12 | 2024 |
| Emergent world representations: Exploring a sequence model trained on a synthetic task. arXiv 2022 K Li, AK Hopkins, D Bau, F Viégas, H Pfister, M Wattenberg arXiv preprint arXiv:2210.13382, 2022 | 11 | 2022 |
| Dialogue action tokens: Steering language models in goal-directed dialogue with a multi-turn planner K Li, Y Wang, F Viégas, M Wattenberg arXiv preprint arXiv:2406.11978, 2024 | 8 | 2024 |
| Unsupervised Discriminative Learning of Sounds for Audio Event Classification S Hornauer, K Li, XY Stella, S Ghaffarzadegan, L Ren International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021 | 8 | 2021 |
| When Bad Data Leads to Good Models K Li, Y Chen, F Viégas, M Wattenberg International Conference on Machine Learning (ICML), 2025 | 5 | 2025 |
| Communicating Activations Between Language Model Agents V Ramesh, K Li International Conference on Machine Learning (ICML), 2025 | 5 | 2025 |
| Towards Tokenized Human Dynamics Representation K Li, X Sun, Z Wu, F Wei, S Lin arXiv preprint arXiv:2111.11433, 2021 | 3 | 2021 |
| What Does it Mean for a Neural Network to Learn a" World Model"? K Li, F Viégas, M Wattenberg arXiv preprint arXiv:2507.21513, 2025 | 1 | 2025 |
Martin WattenbergHarvard University / Google ResearchVerified email at seas.harvard.edu
