Tianyang Hu

Reinforcing Diffusion Models by Direct Group Preference Optimization

Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling

Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture

PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention

SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From

From Divergence to Normalized Similarity:A Symmetric and Scalable Topological Toolkit for Representation Analysis

Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation

The Buffer Mechanism for Multi-Step Information Reasoning in Language Models

Noise Consistency Training: A Native Approach for One-step Generator in Learning Additional Controls

You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs

Elucidating the design space of language models for image generation

Elucidating the Design Space of Language Models for Image Generation