Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation | Alexi Gladstone et al. | ResearchPod

Transcript: Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation

Alex: Welcome to another episode of ResearchPod. Today, we're looking at a paper that asks a fundamental question about how we train artificial intelligence.

Sam: Right. For about a decade now, the main levers for improving AI have been making models larger and feeding them more data. But there's a third thing that's often overlooked: the training process itself. This paper explores a new approach the authors call Explorative Modeling.

Alex: So the question is whether we can improve AI by changing how we train it, not just how big it is or how much data it sees?

Sam: Exactly. And to understand why that matters, you need to understand a problem that current generative models run into. Imagine you're trying to learn what a "dog" looks like, but your training data includes huskies, chihuahuas, and great danes. If you try to learn all of those at once by averaging them together, you end up with a blurry, in-between shape that doesn't look like any real dog. In technical terms, this is called a "multimodal distribution"—a situation where there are many different valid answers, not just one.

Alex: So it's like trying to hit a target, but the model is always aiming for the middle of a cluster of targets instead of picking one specific bullseye.

Sam: That's a good way to put it. And current models have a workaround for this. Rather than trying to solve the whole problem in one go, they break the generation process into many tiny, manageable steps. Each small step is simple enough that the "averaging" problem doesn't cause much damage. But this workaround has a cost.

Alex: What's the cost?

Sam: The cost is that you lose what's called "end-to-end" training. In an end-to-end system, the way the model generates an output during training is identical to how it does it in the real world. When you break a task into many separate steps, you introduce a gap between training and real-world use. Small errors in each step accumulate, and by the end, you can have a meaningful gap between what the model learned and what it actually needs to do.

Alex: So the research team is trying to get the best of both worlds—end-to-end training, but without the blurring problem?

Sam: That's the goal. Here's how they do it. Instead of changing the generation process, they change the training loop. At each training step, the model generates several candidate outputs—several arrows, if you like—and then it only learns from the one that came closest to the real data. The others are discarded.

Alex: Oh—so it's like a student practicing archery who fires several arrows and only studies the one that landed closest to the bullseye. You're not averaging where all the arrows landed; you're learning from your best shot.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation

Alexi Gladstone, Heng Ji, Yilun Du

Jul 29, 2026·5:14·arxiv·Original Paper

Explorative ModelingEnd-to-End Generative ModelingPretraining AxisMultimodal DistributionsEnd-to-end trainingGenerative expressivity

Listen

5 min

Briefing

Research Question

Generative modeling has historically struggled to achieve true end-to-end training, unlike other deep learning domains. Current scalable models (like diffusion or autoregressive models) rely on factoring the generation process into many small, unimodal steps to avoid mode blurring. The authors investigate whether it is possible to achieve end-to-end generative modeling by instead factoring the training loop, thereby enabling models to handle multimodal distributions without sacrificing the end-to-end nature of the inference process.

Approach

The authors introduce Explorative Modeling (XM), a paradigm where the model generates K candidate samples at each training step and is trained only on the candidate closest to the ground truth. This process, termed "best-of-K" training, forces the model to commit to specific modes of the data distribution rather than predicting the average (the mean) of multiple modes. By increasing K, the model's "generative expressivity"—its ability to represent distinct data modes—scales independently of model parameters or data volume.

Main Findings

Exploration acts as a third, critical scaling axis alongside parameters and data. The authors demonstrate that increasing exploration monotonically improves performance across continuous and discrete domains, including images, video, and language. Notably, these gains are amplified at scale: as models and datasets grow, the performance benefits of exploration increase significantly. Furthermore, XM enables end-to-end reconstructive modeling that matches the performance of diffusion-based control tasks while requiring 16–256x fewer inference steps.

Why It Matters

This work challenges the necessity of factoring generation into complex, multi-step procedures. By proving that training-loop factorization can achieve state-of-the-art results, the authors provide a pathway to more efficient, end-to-end generative models. This approach not only improves sample and parameter efficiency but also offers a new lever for researchers to optimize generalization by trading off training compute for increased generative expressivity.

Key Terms and Definitions

Explorative Modeling — A training paradigm that factors the training loop by exploring multiple candidate matches between model generations and data, training only on the best match.
Generative Expressivity — The number of distinct modes a generative model's training objective allows it to capture, which the authors identify as a fundamental scaling axis.
Mode Blurring — A phenomenon where a model predicts the average of multiple valid data modes, resulting in outputs that do not correspond to any real data point.
End-to-End Generation — A property where a model samples during inference using the exact same procedure it was trained on, avoiding the train-inference mismatch common in multi-step generative models.
Mode Forcing — The design of a reconstructive objective intended to force a model to capture distinct data modes rather than averaging them.

Abstract

The deep learning revolution, kicked off by AlexNet, taught us that end-to-end training beats decomposing a problem into hand-designed stages. Generative modeling, however, has remained the exception-despite generative models being remarkably capable, they are still not trained end-to-end. This is because, at its core, generative modeling is about handling distributions with many modes, and existing scalable approaches handle this the same way, by factoring the generation procedure, which prevents end-to-end generation. In this work, we introduce Explorative Modeling, a new paradigm that instead factors the training loop, exploring K candidate matches between model generations and data, and training on the best, so predictions commit to modes rather than blurring them. We find Explorative Models (XMs) useful in two settings. First, increasing exploration adds a third pretraining axis beyond parameters and data for existing generative models-where scaling exploration monotonically improves performance across both continuous and discrete domains (images, video, and language). Notably, gains from exploration increase with scale, climbing from 7% to 36% as data scales and from 13% to 23% as models grow, with efficiency gains more than doubling at 3x the compute. Concretely, exploration improves FLOP efficiency by 4.1x, sample efficiency by 6.2x, parameter efficiency by 47%, lifts the strongest of image-generation recipes to a near-state-of-the-art 1.43 FID on ImageNet without guidance, enables scaling how end-to-end existing models are, and unlocks scaling generalization. Second, XMs enable end-to-end reconstructive generative modeling, matching diffusion on control tasks with 16-256x fewer inference steps. Together, these results establish XMs as both a new pretraining axis for existing generative models and a standalone end-to-end generative modeling paradigm.

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation: Research Paper Podcast