arXiv Machine Learning
Jul 16
Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes
arXiv:2607. 13188v1 Announce Type: new Abstract: Human cognition does not separate understanding and generation.
Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes
Human cognition does not separate understanding and generation. A teacher at a whiteboard speaks and draws $\textit{together}$, each modality reshapes the other.
Related stories
Hugging Face Trending Papers
Jun 17
Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning
Unified multimodal models (UMMs) interleave generated ''visual thoughts'' (VTs) with text reasoning to improve spatial tasks. This incurs roughly an order-of-magnitude inference cost from multi-step diffusion.
arXiv Computer Vision
Aug 26
Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning
arXiv:2606.18974v3 Announce Type: replace Abstract: Unified multimodal models (UMMs) interleave generated ''visual thoughts'' (VTs) with text reasoning to improve spatial tasks. This incurs roughly a...
arXiv AI
3d ago
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
UniEvo‑VL is a self‑evolving framework that lets multimodal models improve themselves by using their own critiques as privileged information. The method trains a single model to act as both teacher and student, minimizing divergence between their diffusion distributions over sampling trajectories. Experiments on Qwen‑image‑2512 show significant gains in image generation metrics, and stronger external critics further raise the improvement ceiling, though results vary across tasks.
arXiv AI
Aug 19
Where a New Concept Must Enter: Entry Point Gates Cross-Task Usability in Unified Multimodal Models
The paper investigates how new concepts can be integrated into unified multimodal models (UMMs) by separating generation and understanding objectives through a novel visual entity bound to a single task direction. Experiments show that the effectiveness of cross‑task usability depends on where the concept is injected into the shared computation, with a mid‑stack alignment objective achieving high concept acquisition with minimal loss to overall performance. The study highlights that unified weights alone are insufficient; the two directions must share a semantic format at the entry point for efficient concept integration.
Hugging Face Trending Papers
4d ago
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
Modern multimodal models bring generation and understanding into a single unified system, which enables them to provide and learn from their own feedback. Motivated by this unified capacity, we introd...
arXiv AI
Jul 1
Surprise as a Signal for Plasticity and Metacognition
arXiv:2606. 31495v1 Announce Type: new Abstract: We study a single idea across two settings: that a prediction-error signal, computed by a small predictor over the latent space of a frozen encoder, can serve both as a gate on plasticity and as a substrate for metacognition.
arXiv Computer Vision
Sep 14
Retrieved Images as Visual Thought: Training-Free Multimodal In-Context Learning for the Open-vs-Closed Gap
ReVisIT is a train‑free framework that turns retrieved image‑label pairs into units of visual thought, combining structured class definitions, multimodal retrieval, and alternating user/assistant injection before joint decoding. On several benchmarks—including Fast Open MiniImageNet, Bongard‑OpenWorld, and the newly released MAAC‑Bench—ReVisIT achieves performance comparable to or surpassing large, trained models while using far fewer parameters. The approach demonstrates that high‑quality retrieval and a simple turns layer can provide a universal performance boost across diverse multimodal tasks.
arXiv Machine Learning
Jul 22
Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning
arXiv:2607. 18615v1 Announce Type: cross Abstract: Machine unlearning for vision-language models (VLMs) remains underexplored.
Hugging Face Trending Papers
Jul 21
Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning
Machine unlearning for vision-language models (VLMs) remains underexplored. Unlike language models, VLMs combine a language backbone with visual components, which makes unlearning more complex.
arXiv AI
Jun 26
Reconstruction Alignment Improves Unified Multimodal Models
arXiv:2509. 07295v4 Announce Type: replace-cross Abstract: Unified multimodal models (UMMs) unify visual understanding and generation within a single architecture.
arXiv Machine Learning
Jul 31
Latent-Kernel Discrete Flow Maps for Few-Step Generation
arXiv:2607. 27529v1 Announce Type: new Abstract: Discrete diffusion and flow-matching models denoise a sequence over many steps, but to keep each step cheap, they factorize the transition across positions and decide every token independently.