arXiv:2607. 02291v1 Announce Type: new Abstract: Conventional reinforcement learning strategies for visual generation typically employ sample-wise reward functions, yet this practice frequently results in reward hacking that degrades image diversity and introduces visual anomalies.
arXiv:2603. 23086v2 Announce Type: replace Abstract: Autoregressive (AR) models are highly effective for image generation, yet their standard maximum-likelihood estimation training lacks direct optimization for sample quality and diversity.
arXiv:2606. 02521v1 Announce Type: new Abstract: One-step text-to-image generators are attractive for deployment because they generate an image with a single forward pass, but preference finetuning them remains difficult: standard alignment methods often rely on policy likelihoods, denoising trajectories, differentiable reward gradients, or test-time optimization.
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.
The paper introduces DRILL, a bilevel training framework that optimizes world models for policy improvement rather than pixel accuracy. DRILL-VWI reweights prediction errors using policy visitation and model confidence, while DRILL-IMG employs meta‑gradients to directly maximize downstream policy returns. Experiments on manipulation simulators show DRILL-IMG boosts success rates by 13.1 points over WMPO and 7.9 points over RLVR-World, demonstrating that world models can be more effectively trained using policy gradients.
The paper introduces RECAP, a training method that enhances vision‑language models by incorporating temporally localized reactivation of image evidence—called visual revisit—into the reinforcement learning process. Visual revisit peaks are shown to predict correctness and causally improve performance; masking them hurts accuracy more than masking non‑peaks, while adding revisit peaks to failed reasoning partially restores correct answers. RECAP applies revisit‑conditioned advantage estimation, dynamic discounting, and gated value prediction to propagate final rewards through visually important reasoning steps, achieving significant gains on HallusionBench and other benchmarks without extra rewards or inference‑time changes.
arXiv:2606. 19162v1 Announce Type: new Abstract: Score- and flow-matching models often rely on preference-based reinforcement learning for two purposes: aligning with subjective preferences and, surprisingly, recovering properties such as visual realism and coherent object structure that matching-based training is intended to learn from the data itself.
The paper introduces DRILL, a bilevel training framework that optimizes world models for policy improvement rather than pixel accuracy. By reweighting prediction errors with policy visitation and confidence (DRILL‑VWI) or using a full meta‑gradient approach (DRILL‑IMG), the authors demonstrate significant gains in downstream policy success rates across multiple manipulation simulators. The work shows that world models can be more effectively trained using the policy gradients they generate, rather than relying solely on pixel‑level prediction metrics.
The paper introduces Priming Models, a two‑stage framework for training one‑step generative models. First, the model is trained on a reconstruction objective such as pixel‑space denoising at a fixed noise level, then it undergoes feature‑space distributional post‑training. This simple reconstruction stage alone is shown to eliminate the difficulty of distributional training, leading to significant improvements in training compute versus generation quality across tasks like class‑conditional image generation, text‑to‑image generation, and world modeling, with a state‑of‑the‑art FID of 1.19 on ImageNet 256×256 using about one‑tenth the compute of previous methods.
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:2606. 27180v1 Announce Type: cross Abstract: Sparse rewards are inherently challenging for reinforcement learning agents as they lack intermediate feedback to guide exploration and to correctly attribute the sparse success rewards to relevant parts of the trajectory.
arXiv:2610.16224v1 Announce Type: cross Abstract: Text-to-image models have made remarkable progress in visual fidelity and instruction following, yet complex compositional generation remains challen...