Yu Huang

15

Papers

16

Total Citations

Papers (15)

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

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

A Theoretical Analysis of Self-Supervised Learning for Vision Transformers

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

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

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

In-context Convergence of Transformers

Accelerating Convergence of Score-Based Diffusion Models, Provably

BetterV: Controlled Verilog Generation with Discriminative Guidance

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

Star with Bilinear Mapping

Domain Generalization in CLIP via Learning with Diverse Text Prompts

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

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

Provable Generalization of Overparameterized Meta-learning Trained with SGD