The paper introduces Next Token Imagination (NTI), a technique for visual autoregressive generation that allows a model to predict beyond the ground-truth next token while staying within a defined visual distribution. By enabling the model to explore plausible but unseen visual realizations, NTI addresses the limitation of training only on observed data. Experiments on ImageNet demonstrate that NTI consistently improves image fidelity, approaching the performance of state‑of‑the‑art diffusion and autoregressive models with a smaller model and lower training cost.
arXiv:2611.06838v1 Announce Type: new Abstract: Autoregressive image generation has recently emerged as a competitive visual generation paradigm, yet its generation order is often predefined or heuri...
arXiv:2607. 27372v1 Announce Type: new Abstract: The deep learning revolution, kicked off by AlexNet, taught us that end-to-end training beats decomposing a problem into hand-designed stages.
arXiv:2610.39913v2 Announce Type: replace Abstract: We present an inference-time approach that enhances the visual diversity of image sets generated by text-to-image models, without compromising the...
arXiv:2608. 00716v1 Announce Type: cross Abstract: Robust detection of generated images is critical to counter the misuse of generative models.
arXiv:2607. 09024v1 Announce Type: cross Abstract: Driven by next-token prediction, NLP shifted from task-specific models into powerful generalist foundation models.
Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Models introduces the VIG‑Sampler, a method that prioritizes tokens for decoding based on their attention to image tokens and penalizes redundancy in image‑attention distributions. The approach aims to improve the quality of multimodal generation by selecting more informative tokens during diffusion decoding. Experiments on seven captioning and VQA benchmarks with three open‑source dMLLMs show that VIG‑Sampler outperforms the Info‑Gain Sampler by an average of 19.3 CIDEr points and achieves better COCO Caption results using only half as many decoding steps.
The paper introduces MTAR, a training framework for autoregressive image generation that enhances performance through multi-token prediction, token-level contrastive regularization, and semantic dropping. These components address sparse supervision, improve representation discriminability, and accelerate training without affecting inference. On ImageNet, MTAR outperforms LlamaGen with lower FID and faster training, achieving comparable results in only a third of the iterations.
arXiv:2610.30724v2 Announce Type: replace-cross Abstract: Video provides a natural source of supervision: what happens next serves as a learning signal for visual world modeling. Yet masked video pre...
EvoWorld introduces a framework that couples a vision‑language model with a segment‑autoregressive video renderer to enable generative video models to reason about world evolution beyond visual fidelity. The system maintains an evolving account of the world, infers event consequences, and renders causally plausible outcomes even when events occur out of sight. The accompanying EvoWorld‑Data and EvoWorld‑Bench datasets provide training and evaluation for event realization, causal reactions, and revisit consistency.
arXiv:2604. 20329v3 Announce Type: replace-cross Abstract: Recent works show that image and video generators exhibit zero-shot visual understanding behaviors, in a way reminiscent of how LLMs develop emergent capabilities of language understanding and reasoning from generative pretraining.
The article surveys how diffusion and flow-based generative models learn rich visual representations and how these representations can be used to improve generation and other perception tasks. It introduces a three-tier framework that categorizes work into improving generative quality via representation learning, extracting representations for perception, and developing unified applications. The survey covers downstream tasks such as image classification, dense prediction, instance-level perception, and annotation-scarce scenarios, offering a taxonomy and highlighting future research directions.
arXiv:2605.27310v2 Announce Type: replace Abstract: Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they reason in language and discard the fine-grained geometry t...