arXiv Computer Vision
Self-correction Optimization for Interleaved Multimodal Generation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
Aug 24
Direct, Parallel, or Sequential? A Comparative Study of Training-Free Multi-Subject Image-to-Video Generation
Text-conditioned image-to-video (I2V) generation has advanced rapidly, yet generating videos with multiple subjects remains challenging. A model must simultaneously preserve the appearance of each sub...
arXiv Computer Vision
Aug 25
Direct, Parallel, or Sequential? A Comparative Study of Training-Free Multi-Subject Image-to-Video Generation
arXiv:2608.22819v1 Announce Type: new Abstract: Text-conditioned image-to-video (I2V) generation has advanced rapidly, yet generating videos with multiple subjects remains challenging. A model must s...
arXiv AI
Aug 5
Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement
arXiv:2608. 03733v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved remarkable performance across vision-language tasks, but their progress depends heavily on large-scale, high-quality multimodal data that are costly to annotate.
arXiv Computer Vision
3d ago
Dreaming in Flow: Bidirectional Self-Refinement for Unified Multimodal Models
arXiv:2609.08282v2 Announce Type: replace Abstract: Unified multimodal models can generate images and interpret them, but their two capabilities are usually optimized with separate supervision. We in...
Hugging Face Trending Papers
Aug 4
Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement
Multimodal large language models (MLLMs) have achieved remarkable performance across vision-language tasks, but their progress depends heavily on large-scale, high-quality multimodal data that are costly to annotate. Self-augmentation offers a promising alternative by enabling models to expand their own training data without external supervision.
Hugging Face Trending Papers
Sep 28
BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusion
BiMoGen introduces a unified masked discrete diffusion framework for bidirectional motion‑text generation, addressing the limitations of autoregressive models in capturing bidirectional dependencies between language and motion. The approach employs a two‑stage training strategy—decoupled uni‑ and cross‑modal pretraining followed by supervised fine‑tuning—to establish robust cross‑modal correspondence, and incorporates Generation‑Aware Self‑Correction to mitigate error propagation during inference. Experiments on HumanML3D and KIT‑ML show competitive performance on both text‑to‑motion and motion‑to‑text tasks, demonstrating the effectiveness of the proposed training and correction mechanisms.