PATTS: Parallel-Aware Test-Time Scaling for Thought-Image Generation in Multimodal Discrete Diffusion LLMs
cs.CV
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/Ringo-Star/PATTS
Terminology
Sources
- LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
- Emerging Properties in Unified Multimodal Pretraining
- Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step
- Test-time Alignment of Diffusion Models without Reward Over-optimization
- Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps
- Large Language Diffusion Models
- Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding
- Rethinking Test Time Scaling for Flow-Matching Generative Models
- Generative Universal Verifier as Multimodal Meta-Reasoner
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs