activity
20232026
most citedUnlocking the Potential of Text-to-Image Diffusion with PAC-Bayesian Theory

2 citations · 3 across the 17 of their papers we have counts for

collaborators
Showing cs.CVShow all

13 papers · 1 filter

cs.CV2026

Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis

Shufan Li, Greg Heinrich, Hanrong Ye +4

We propose Nemotron-Labs-Diffusion-Image, a state-of-the-art masked discrete diffusion model (MDM) for high-resolution text-to-image synthesis. Compared with prior work on masked i…

cs.CV2026

Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization

Shufan Li, Konstantinos Kallidromitis, Akash Gokul +2

Group-advantage-based reinforcement learning methods, such as GRPO and DAPO, have demonstrated strong performance across diverse domains, including mathematical reasoning and text-…

cs.CV2026

SNCE: Geometry-Aware Supervision for Scalable Discrete Image Generation

Shufan Li, Jiuxiang Gu, Kangning Liu +3

Recent advancements in discrete image generation showed that scaling the VQ codebook size significantly improves reconstruction fidelity. However, training generative models with a…

cs.CV2026

LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models

Shufan Li, Yuchen Zhu, Jiuxiang Gu +6

Diffusion language models (dLLMs) recently emerged as a promising alternative to auto-regressive LLMs. The latest works further extended it to multimodal understanding and generati…

cs.CV2025

Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Models

Shufan Li, Jiuxiang Gu, Kangning Liu +4

Masked Discrete Diffusion Models (MDMs) have achieved strong performance across a wide range of multimodal tasks, including image understanding, generation, and editing. However, t…

cs.CV2025

Accelerating Inference of Masked Image Generators via Reinforcement Learning

Pranav Subbaraman, Shufan Li, Siyan Zhao +1

Masked Generative Models (MGM)s demonstrate strong capabilities in generating high-fidelity images. However, they need many sampling steps to create high-quality generations, resul…