Qinzi Zhang

papers

112

total citations

papers (12)

LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models

COLM 2025arXiv

citations

Threshold-Consistent Margin Loss for Open-World Deep Metric Learning

ICLR 2024arXiv

citations

Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning

NEURIPS 2025arXiv

citations

MindSimulator: Exploring Brain Concept Localization via Synthetic fMRI

ICLR 2025arXiv

citations

Revisiting Large-Scale Non-convex Distributionally Robust Optimization

ICLR 2025

citations

Neural Poisson Solver: A Universal and Continuous Framework for Natural Signal Blending

ECCV 2024arXiv

citations

Effective Length Extrapolation via Dimension-Wise Positional Embeddings Manipulation

COLM 2025arXiv

citations

Physically Plausible Color Correction for Neural Radiance Fields

ECCV 2024

citations

Revealing Multimodal Causality with Large Language Models

NEURIPS 2025arXiv

citations

Qinzi Zhang

papers (12)

RMB: Comprehensively benchmarking reward models in LLM alignment

SELF-EVOLVED REWARD LEARNING FOR LLMS

Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs

LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models

Threshold-Consistent Margin Loss for Open-World Deep Metric Learning

Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning

MindSimulator: Exploring Brain Concept Localization via Synthetic fMRI

Revisiting Large-Scale Non-convex Distributionally Robust Optimization

Neural Poisson Solver: A Universal and Continuous Framework for Natural Signal Blending

Effective Length Extrapolation via Dimension-Wise Positional Embeddings Manipulation

Physically Plausible Color Correction for Neural Radiance Fields

Revealing Multimodal Causality with Large Language Models

papers (12)

RMB: Comprehensively benchmarking reward models in LLM alignment

SELF-EVOLVED REWARD LEARNING FOR LLMS

Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs

LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models

Threshold-Consistent Margin Loss for Open-World Deep Metric Learning

Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning

MindSimulator: Exploring Brain Concept Localization via Synthetic fMRI

Revisiting Large-Scale Non-convex Distributionally Robust Optimization

Neural Poisson Solver: A Universal and Continuous Framework for Natural Signal Blending

Effective Length Extrapolation via Dimension-Wise Positional Embeddings Manipulation

Physically Plausible Color Correction for Neural Radiance Fields

Revealing Multimodal Causality with Large Language Models