Hao Cheng

Affiliations

Microsoft Research

papers

2,313

total citations

papers (20)

MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

ICLR 2024arXiv

1,235

citations

Removing the Background by Adding the Background: Towards Background Robust Self-Supervised Video Representation Learning

CVPR 2021arXiv

111

citations

Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians

ECCV 2020arXiv

citations

DisCo: Remedying Self-Supervised Learning on Lightweight Models with Distilled Contrastive Learning

ECCV 2022arXiv

citations

Filter Grafting for Deep Neural Networks

CVPR 2020arXiv

citations

Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models

ICLR 2024arXiv

citations

Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning

ICML 2025arXiv

citations

DyFADet: Dynamic Feature Aggregation for Temporal Action Detection

ECCV 2024arXiv

citations

Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI

CVPR 2024arXiv

citations

Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

ICLR 2025arXiv

citations

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models

CVPR 2025arXiv

citations

TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention

ICCV 2025

citations

FedCompetitors: Harmonious Collaboration in Federated Learning with Competing Participants

AAAI 2024arXiv

citations

ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models

CVPR 2024arXiv

citations

Adaptive Decision Boundary for Few-Shot Class-Incremental Learning

AAAI 2025arXiv

citations

Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual

CVPR 2025arXiv

citations

Frequency Guidance Matters in Few-Shot Learning

ICCV 2023

citations

Hao Cheng

Affiliations

papers (20)

MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models

Augmenting Language Models with Long-Term Memory

Pruning Filter in Filter

Removing the Background by Adding the Background: Towards Background Robust Self-Supervised Video Representation Learning

Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians

DisCo: Remedying Self-Supervised Learning on Lightweight Models with Distilled Contrastive Learning

Filter Grafting for Deep Neural Networks

Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models

Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning

DyFADet: Dynamic Feature Aggregation for Temporal Action Detection

Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI

Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models

TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention

FedCompetitors: Harmonious Collaboration in Federated Learning with Competing Participants

ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models

Adaptive Decision Boundary for Few-Shot Class-Incremental Learning

Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual

Frequency Guidance Matters in Few-Shot Learning

papers (20)

MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models

Augmenting Language Models with Long-Term Memory

Pruning Filter in Filter

Removing the Background by Adding the Background: Towards Background Robust Self-Supervised Video Representation Learning

Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians

DisCo: Remedying Self-Supervised Learning on Lightweight Models with Distilled Contrastive Learning

Filter Grafting for Deep Neural Networks

Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models

Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning

DyFADet: Dynamic Feature Aggregation for Temporal Action Detection

Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI

Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models

TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention

FedCompetitors: Harmonious Collaboration in Federated Learning with Competing Participants

ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models

Adaptive Decision Boundary for Few-Shot Class-Incremental Learning

Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual

Frequency Guidance Matters in Few-Shot Learning