Bo Pang

papers

1,378

total citations

papers (15)

Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts

CVPR 2024arXiv

citations

Semantic Segmentation by Early Region Proxy

CVPR 2022arXiv

citations

Learning Probabilistic Models from Generator Latent Spaces with Hat EBM

NEURIPS 2022arXiv

citations

PGT: A Progressive Method for Training Models on Long Videos

CVPR 2021arXiv

citations

Latent Thought Models with Variational Bayes Inference-Time Computation

ICML 2025arXiv

citations

Learning Multi-layer Latent Variable Model via Variational Optimization of Short Run MCMC for Approximate Inference

ECCV 2020arXiv

citations

Unsupervised 3D Point Cloud Representation Learning by Triangle Constrained Contrast for Autonomous Driving

CVPR 2023

citations

Bo Pang

papers (15)

Human Pose Regression With Residual Log-Likelihood Estimation

TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model

On Scaling Up a Multilingual Vision and Language Model

Learning Latent Space Energy-Based Prior Model

Asynchronous Interaction Aggregation for Action Detection

Trajectory Prediction With Latent Belief Energy-Based Model

Joint Training of Variational Auto-Encoder and Latent Energy-Based Model

Unsupervised Visual Representation Learning by Synchronous Momentum Grouping

Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts

Semantic Segmentation by Early Region Proxy

Learning Probabilistic Models from Generator Latent Spaces with Hat EBM

PGT: A Progressive Method for Training Models on Long Videos

Latent Thought Models with Variational Bayes Inference-Time Computation

Learning Multi-layer Latent Variable Model via Variational Optimization of Short Run MCMC for Approximate Inference

Unsupervised 3D Point Cloud Representation Learning by Triangle Constrained Contrast for Autonomous Driving

papers (15)

Human Pose Regression With Residual Log-Likelihood Estimation

TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model

On Scaling Up a Multilingual Vision and Language Model

Learning Latent Space Energy-Based Prior Model

Asynchronous Interaction Aggregation for Action Detection

Trajectory Prediction With Latent Belief Energy-Based Model

Joint Training of Variational Auto-Encoder and Latent Energy-Based Model

Unsupervised Visual Representation Learning by Synchronous Momentum Grouping

Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts

Semantic Segmentation by Early Region Proxy

Learning Probabilistic Models from Generator Latent Spaces with Hat EBM

PGT: A Progressive Method for Training Models on Long Videos

Latent Thought Models with Variational Bayes Inference-Time Computation

Learning Multi-layer Latent Variable Model via Variational Optimization of Short Run MCMC for Approximate Inference

Unsupervised 3D Point Cloud Representation Learning by Triangle Constrained Contrast for Autonomous Driving