Reconstruction Alignment Improves Unified Multimodal Models
Paper • 2509.07295 • Published • 40
paper seminar_251001
-
-
F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions
Paper • 2509.06951 • Published • 33 -
UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward
Paper • 2509.06818 • Published • 29 -
Interleaving Reasoning for Better Text-to-Image Generation
Paper • 2509.06945 • Published • 16 -
RewardDance: Reward Scaling in Visual Generation
Paper • 2509.08826 • Published • 73 -
Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling
Paper • 2509.01624 • Published • 7 -
Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference
Paper • 2509.06942 • Published • 19 -
Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation
Paper • 2509.15185 • Published • 29 -
LLM-I: LLMs are Naturally Interleaved Multimodal Creators
Paper • 2509.13642 • Published • 9 -
Image Tokenizer Needs Post-Training
Paper • 2509.12474 • Published • 9 -
InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis
Paper • 2509.10441 • Published • 31 -
HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning
Paper • 2509.08519 • Published • 130 -
MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement
Paper • 2509.01977 • Published • 13 -
GenCompositor: Generative Video Compositing with Diffusion Transformer
Paper • 2509.02460 • Published • 26 -
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Paper • 2508.20751 • Published • 90 -
Mixture of Contexts for Long Video Generation
Paper • 2508.21058 • Published • 35 -
MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
Paper • 2509.16197 • Published • 58 -
Lynx: Towards High-Fidelity Personalized Video Generation
Paper • 2509.15496 • Published • 13 -
OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models
Paper • 2509.17627 • Published • 66 -
Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation
Paper • 2509.19244 • Published • 12 -
Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation
Paper • 2509.18824 • Published • 23 -
VChain: Chain-of-Visual-Thought for Reasoning in Video Generation
Paper • 2510.05094 • Published • 38 -
Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs
Paper • 2509.25771 • Published • 11 -
Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation
Paper • 2510.01284 • Published • 37 -
Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
Paper • 2510.02283 • Published • 98 -
UltraGen: High-Resolution Video Generation with Hierarchical Attention
Paper • 2510.18775 • Published • 18