arXiv Computer Vision
PONDER: Learning to Generate in the Right Order
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Jul 3
Optimizing Visual Generative Models via Distribution-wise Rewards
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 Machine Learning
Jul 13
Policy-based Tuning of Autoregressive Image Models with Instance- and Distribution-Level Rewards
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 Machine Learning
Jun 2
Drifting Preference Optimization for One-Step Generative Models
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.
arXiv Computer Vision
Oct 28
Visual Autoregressive Generation with Next Token Imagination
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.
Hugging Face Trending Papers
Oct 22
DRILL: Training World Models to Improve Policies, Not Predict Pixels
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.
arXiv Computer Vision
Oct 23
RECAP: Looking Once Is Not Enough for Vision-Language Reasoning
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.