Nan Yang

papers

2,917

total citations

papers (12)

MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers

NEURIPS 2020arXiv

1,843

citations

D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry

CVPR 2020arXiv

430

citations

Generative Representational Instruction Tuning

ICLR 2025arXiv

222

citations

PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training

ICLR 2024arXiv

103

citations

MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments From a Single Moving Camera

CVPR 2021arXiv

citations

Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability

ICLR 2025arXiv

citations

Class and Attribute-Aware Logit Adjustment for Generalized Long-Tail Learning

AAAI 2025

citations

Nan Yang

papers (12)

MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers

D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry

Generative Representational Instruction Tuning

PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training

MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments From a Single Moving Camera

Learning to Rank in Generative Retrieval

Behind the Scenes: Density Fields for Single View Reconstruction

Sonata: Self-Supervised Learning of Reliable Point Representations

Chain-of-Retrieval Augmented Generation

SMamba: Sparse Mamba for Event-based Object Detection

Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability

Class and Attribute-Aware Logit Adjustment for Generalized Long-Tail Learning

papers (12)

MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers

D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry

Generative Representational Instruction Tuning

PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training

MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments From a Single Moving Camera

Learning to Rank in Generative Retrieval

Behind the Scenes: Density Fields for Single View Reconstruction

Sonata: Self-Supervised Learning of Reliable Point Representations

Chain-of-Retrieval Augmented Generation

SMamba: Sparse Mamba for Event-based Object Detection

Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability

Class and Attribute-Aware Logit Adjustment for Generalized Long-Tail Learning