Paul Pu Liang

papers

650

total citations

papers (16)

Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning

CVPR 2022arXiv

217

citations

Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction

CVPR 2024arXiv

118

citations

Factorized Contrastive Learning: Going Beyond Multi-view Redundancy

NEURIPS 2023arXiv

citations

Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework

NEURIPS 2023arXiv

citations

Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals

NEURIPS 2023arXiv

citations

VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks

ICLR 2025arXiv

citations

What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains

NEURIPS 2025arXiv

citations

Diverse and Admissible Trajectory Prediction through Multimodal Context Understanding

ECCV 2020

citations

Lecture Presentations Multimodal Dataset: Towards Understanding Multimodality in Educational Videos

ICCV 2023

citations

Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions

NEURIPS 2025arXiv

citations

Paul Pu Liang

papers (16)

Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning

Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction

Factorized Contrastive Learning: Going Beyond Multi-view Redundancy

Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework

Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals

VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks

PACS: A Dataset for Physical Audiovisual Commonsense Reasoning

Localized Symbolic Knowledge Distillation for Visual Commonsense Models

CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models

FLHetBench: Benchmarking Device and State Heterogeneity in Federated Learning

Progressive Compositionality in Text-to-Image Generative Models

OS-ATLAS: Foundation Action Model for Generalist GUI Agents

What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains

Diverse and Admissible Trajectory Prediction through Multimodal Context Understanding

Lecture Presentations Multimodal Dataset: Towards Understanding Multimodality in Educational Videos

Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions

papers (16)

Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning

Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction

Factorized Contrastive Learning: Going Beyond Multi-view Redundancy

Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework

Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals

VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks

PACS: A Dataset for Physical Audiovisual Commonsense Reasoning

Localized Symbolic Knowledge Distillation for Visual Commonsense Models

CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models

FLHetBench: Benchmarking Device and State Heterogeneity in Federated Learning

Progressive Compositionality in Text-to-Image Generative Models

OS-ATLAS: Foundation Action Model for Generalist GUI Agents

What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains

Diverse and Admissible Trajectory Prediction through Multimodal Context Understanding

Lecture Presentations Multimodal Dataset: Towards Understanding Multimodality in Educational Videos

Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions