Jiawei Chen

Affiliations

Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences

papers

782

total citations

papers (18)

Benchmarking Large Language Models in Retrieval-Augmented Generation

AAAI 2024arXiv

475

citations

BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis

NEURIPS 2022arXiv

citations

MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation

CVPR 2025arXiv

citations

Advancing Loss Functions in Recommender Systems: A Comparative Study with a Rényi Divergence-Based Solution

AAAI 2025arXiv

citations

ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers

ICCV 2025arXiv

citations

Towards a Unified Framework of Clustering-based Anomaly Detection

ICML 2025arXiv

citations

Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness–Generalization Perspective

NEURIPS 2025arXiv

citations

Learning Counterfactual Outcomes Under Rank Preservation

NEURIPS 2025arXiv

citations

BloomScene: Lightweight Structured 3D Gaussian Splatting for Crossmodal Scene Generation

AAAI 2025arXiv

citations

The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model

ICLR 2025arXiv

citations

Self-Supervised CycleGAN for Object-Preserving Image-to-Image Domain Adaptation

ECCV 2020

citations

Speech-T: Transducer for Text to Speech and Beyond

NEURIPS 2021

citations

Tree of Preferences for Diversified Recommendation

NEURIPS 2025arXiv

citations

Jiawei Chen

Affiliations

papers (18)

Benchmarking Large Language Models in Retrieval-Augmented Generation

BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis

Distilling Holistic Knowledge With Graph Neural Networks

DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation

Understanding Contrastive Learning via Distributionally Robust Optimization

OpenGSL: A Comprehensive Benchmark for Graph Structure Learning

Debiased Multimodal Understanding for Human Language Sequences

MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation

Advancing Loss Functions in Recommender Systems: A Comparative Study with a Rényi Divergence-Based Solution

ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers

Towards a Unified Framework of Clustering-based Anomaly Detection

Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness–Generalization Perspective

Learning Counterfactual Outcomes Under Rank Preservation

BloomScene: Lightweight Structured 3D Gaussian Splatting for Crossmodal Scene Generation

The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model

Self-Supervised CycleGAN for Object-Preserving Image-to-Image Domain Adaptation

Speech-T: Transducer for Text to Speech and Beyond

Tree of Preferences for Diversified Recommendation

papers (18)

Benchmarking Large Language Models in Retrieval-Augmented Generation

BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis

Distilling Holistic Knowledge With Graph Neural Networks

DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation

Understanding Contrastive Learning via Distributionally Robust Optimization

OpenGSL: A Comprehensive Benchmark for Graph Structure Learning

Debiased Multimodal Understanding for Human Language Sequences

MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation

Advancing Loss Functions in Recommender Systems: A Comparative Study with a Rényi Divergence-Based Solution

ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers

Towards a Unified Framework of Clustering-based Anomaly Detection

Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness–Generalization Perspective

Learning Counterfactual Outcomes Under Rank Preservation

BloomScene: Lightweight Structured 3D Gaussian Splatting for Crossmodal Scene Generation

The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model

Self-Supervised CycleGAN for Object-Preserving Image-to-Image Domain Adaptation

Speech-T: Transducer for Text to Speech and Beyond

Tree of Preferences for Diversified Recommendation