Get started
Author

Bingbin Liu

Observed name: Liu, Bingbin
Institution: Harvard University
ORCID: 0000-0002-6621-0356
Observed ORCID: 0000-0002-6621-0356
OpenAlex ID: A5007869267
Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction
2020 · Bingbin Liu, Ehsan Adeli, et al. · IEEE Robotics and Automation Letters · 195
PDF
Learning to Decompose and Disentangle Representations for Video Prediction
2018 · Jun-Ting Hsieh, Bingbin Liu, et al. · neural information processing systems · 178
A computer vision system for deep learning-based detection of patient mobilization activities in the ICU
2019 · Serena Yeung, Francesca Rinaldo, et al. · npj Digital Medicine · 125
PDF
Learning to Decompose and Disentangle Representations for Video Prediction
2018 · Hsieh, Jun-Ting, Liu, Bingbin, et al. · arXiv (Cornell University) · 108
PDF
Temporal Modular Networks for Retrieving Complex Compositional Activities in Videos
2018 · Bingbin Liu, Serena Yeung, et al. · Lecture notes in computer science · 67
Transformers Learn Shortcuts to Automata
2022 · Liu, Bingbin, Ash, Jordan T., et al. · arXiv (Cornell University) · 13
PDF
Exposing Attention Glitches with Flip-Flop Language Modeling
2023 · Bingbin Liu, Jordan Ash, et al. · neural information processing systems · 12
PDF
3D Point Cloud-Based Visual Prediction of ICU Mobility Care Activities.
2018 · Bingbin Liu, Michelle Guo, et al. · Machine Learning for Healthcare Conference · 9
Generalized Boosting
2020 · Arun Sai Suggala, Bingbin Liu, et al. · neural information processing systems · 3
Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression
2023 · Zhai, Runtian, Liu, Bingbin, et al. · arXiv (Cornell University) · 2
PDF
When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon
2026 · Zhang, Huaqing, Gai, Jingchu, et al. · arXiv (Cornell University)
PDF
Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling biases
2026 · Liu, Jingwen, Edelman, Ezra, et al. · arXiv (Cornell University)
PDF
The two clocks and the innovation window: When and how generative models learn rules
2026 · Wang, Binxu, Finn, Emma Lucia Byrnes, et al. · arXiv (Cornell University)
PDF
In Good GRACEs: Principled Teacher Selection for Knowledge Distillation
2025 · Panigrahi, Abhishek, Liu, Bingbin, et al. · arXiv (Cornell University)
PDF
Adam or Gauss-Newton? A Comparative Study In Terms of Basis Alignment and SGD Noise
2025 · Liu, Bingbin, Bansal, Rachit, et al. · arXiv (Cornell University)
PDF
Progressive distillation induces an implicit curriculum
2024 · Panigrahi, Abhishek, Liu, Bingbin, et al. · arXiv (Cornell University)
PDF
Improving Instructional Materials with Large Language Models
2024 · Bingbin Liu, Joy He-Yueya · XRDS Crossroads The ACM Magazine for Students
Large Language Models in Education Embracing Opportunities, Confronting Challenges, and Shaping the Next Chapter Together
2024 · Bingbin Liu · XRDS Crossroads The ACM Magazine for Students
TinyGSM: achieving >80% on GSM8k with small language models
2023 · Liu, Bingbin, Bubeck, Sebastien, et al. · arXiv (Cornell University)
PDF
Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars
2023 · Kaiyue Wen, Yuchen Li, et al. · neural information processing systems
PDF
Masked prediction tasks: a parameter identifiability view
2022 · Liu, Bingbin, Hsu, Daniel, et al. · arXiv (Cornell University)
PDF
Masked Prediction: A Parameter Identifiability View
2022 · Bingbin Liu, Daniel Hsu, et al. · neural information processing systems
Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimation
2021 · Liu, Bingbin, Rosenfeld, Elan, et al. · arXiv (Cornell University)
PDF
Contrastive learning of strong-mixing continuous-time stochastic processes
2021 · Liu, Bingbin, Ravikumar, Pradeep, et al. · arXiv (Cornell University)
PDF
A Computer Vision System to Detect Bedside Patient Mobilization
2019 · Yeung, serena, Rinaldo, Francesca, et al. · Infoscience (Ecole Polytechnique Fédérale de Lausanne)
Works count: 25
Citation count: 712
H-index: 8
I10-index: 7
Year
Topic
Type