Nanyun Peng

papers

1,225

total citations

papers (16)

STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models

AAAI 2024arXiv

citations

ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models

ICML 2024arXiv

citations

OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles

NEURIPS 2025arXiv

citations

InsNet: An Efficient, Flexible, and Performant Insertion-based Text Generation Model

NEURIPS 2022arXiv

citations

VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning

CVPR 2025arXiv

citations

Contrastive Visual Data Augmentation

ICML 2025arXiv

citations

DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models

ICML 2024arXiv

citations

Open-Domain Text Evaluation via Contrastive Distribution Methods

ICML 2024arXiv

citations

Verbalized Representation Learning for Interpretable Few-Shot Generalization

ICCV 2025arXiv

citations

Nanyun Peng

papers (16)

An Empirical Study of Training End-to-End Vision-and-Language Transformers

Generalized Decoding for Pixel, Image, and Language

Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone

On Prompt-Driven Safeguarding for Large Language Models

Controllable Text Generation with Neurally-Decomposed Oracle

MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models

DesCo: Learning Object Recognition with Rich Language Descriptions

STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models

ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models

OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles

InsNet: An Efficient, Flexible, and Performant Insertion-based Text Generation Model

VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning

Contrastive Visual Data Augmentation

DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models

Open-Domain Text Evaluation via Contrastive Distribution Methods

Verbalized Representation Learning for Interpretable Few-Shot Generalization

papers (16)

An Empirical Study of Training End-to-End Vision-and-Language Transformers

Generalized Decoding for Pixel, Image, and Language

Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone

On Prompt-Driven Safeguarding for Large Language Models

Controllable Text Generation with Neurally-Decomposed Oracle

MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models

DesCo: Learning Object Recognition with Rich Language Descriptions

STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models

ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models

OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles

InsNet: An Efficient, Flexible, and Performant Insertion-based Text Generation Model

VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning

Contrastive Visual Data Augmentation

DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models

Open-Domain Text Evaluation via Contrastive Distribution Methods

Verbalized Representation Learning for Interpretable Few-Shot Generalization