Yu Huang

papers

719

total citations

papers (15)

MIMO: A Medical Vision Language Model with Visual Referring Multimodal Input and Pixel Grounding Multimodal Output

CVPR 2025arXiv

citations

Parameter-efficient Fine-tuning in Hyperspherical Space for Open-vocabulary Semantic Segmentation

CVPR 2025arXiv

citations

Exploit Your Latents: Coarse-Grained Protein Backmapping with Latent Diffusion Models

AAAI 2025

citations

Understanding Fine-tuning CLIP for Open-vocabulary Semantic Segmentation in Hyperbolic Space

CVPR 2025

citations

Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization

NEURIPS 2025arXiv

citations

A Theoretical Analysis of Self-Supervised Learning for Vision Transformers

ICLR 2025arXiv

citations

Star with Bilinear Mapping

CVPR 2025

citations

A Learnable Discrete-Prior Fusion Autoencoder with Contrastive Learning for Tabular Data Synthesis

AAAI 2024

citations

Domain Generalization in CLIP via Learning with Diverse Text Prompts

CVPR 2025

citations

STAMPsy: Towards SpatioTemporal-Aware Mixed-Type Dialogues for Psychological Counseling

AAAI 2025arXiv

citations

Yu Huang

papers (15)

What Makes Multi-Modal Learning Better than Single (Provably)

BetterV: Controlled Verilog Generation with Discriminative Guidance

In-context Convergence of Transformers

Accelerating Convergence of Score-Based Diffusion Models, Provably

Provable Generalization of Overparameterized Meta-learning Trained with SGD

MIMO: A Medical Vision Language Model with Visual Referring Multimodal Input and Pixel Grounding Multimodal Output

Parameter-efficient Fine-tuning in Hyperspherical Space for Open-vocabulary Semantic Segmentation

Exploit Your Latents: Coarse-Grained Protein Backmapping with Latent Diffusion Models

Understanding Fine-tuning CLIP for Open-vocabulary Semantic Segmentation in Hyperbolic Space

Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization

A Theoretical Analysis of Self-Supervised Learning for Vision Transformers

Star with Bilinear Mapping

A Learnable Discrete-Prior Fusion Autoencoder with Contrastive Learning for Tabular Data Synthesis

Domain Generalization in CLIP via Learning with Diverse Text Prompts

STAMPsy: Towards SpatioTemporal-Aware Mixed-Type Dialogues for Psychological Counseling

papers (15)

What Makes Multi-Modal Learning Better than Single (Provably)

BetterV: Controlled Verilog Generation with Discriminative Guidance

In-context Convergence of Transformers

Accelerating Convergence of Score-Based Diffusion Models, Provably

Provable Generalization of Overparameterized Meta-learning Trained with SGD

MIMO: A Medical Vision Language Model with Visual Referring Multimodal Input and Pixel Grounding Multimodal Output

Parameter-efficient Fine-tuning in Hyperspherical Space for Open-vocabulary Semantic Segmentation

Exploit Your Latents: Coarse-Grained Protein Backmapping with Latent Diffusion Models

Understanding Fine-tuning CLIP for Open-vocabulary Semantic Segmentation in Hyperbolic Space

Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization

A Theoretical Analysis of Self-Supervised Learning for Vision Transformers

Star with Bilinear Mapping

A Learnable Discrete-Prior Fusion Autoencoder with Contrastive Learning for Tabular Data Synthesis

Domain Generalization in CLIP via Learning with Diverse Text Prompts

STAMPsy: Towards SpatioTemporal-Aware Mixed-Type Dialogues for Psychological Counseling