REVIEW 9 cited by
Compositional Generative Modeling: A Single Model is Not All You Need
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Compositional Generative Modeling: A Single Model is Not All You Need
read the original abstract
Large monolithic generative models trained on massive amounts of data have become an increasingly dominant approach in AI research. In this paper, we argue that we should instead construct large generative systems by composing smaller generative models together. We show how such a compositional generative approach enables us to learn distributions in a more data-efficient manner, enabling generalization to parts of the data distribution unseen at training time. We further show how this enables us to program and construct new generative models for tasks completely unseen at training. Finally, we show that in many cases, we can discover separate compositional components from data.
Forward citations
Cited by 9 Pith papers
-
ArchEval: Measuring AI Agents as Computer Architects
LLM agents beat architecture baselines with full simulator harnesses, but only one configuration stays above baseline without feedback, and performance modeling remains weak.
-
Learning to Theorize the World from Observation
NEO is a probabilistic neural model that induces compositional programs as a learned Language of Thought from non-textual observations and executes them via a shared transition model to enable explanation-driven gener...
-
Long-Text-to-Image Generation via Compositional Prompt Decomposition
PRISM lets pre-trained text-to-image models handle long prompts by breaking them into compositional parts, predicting noise separately, and merging outputs via energy-based conjunction, matching fine-tuned models whil...
-
Multi-Modal Manipulation via Multi-Modal Policy Consensus
A policy that factorizes into modality-specific diffusion models combined by a learned router network for adaptive multi-modal robotic manipulation.
-
History-Guided Video Diffusion
DFoT enables flexible history conditioning in video diffusion, with history guidance methods that boost temporal consistency and support long rollouts.
-
Learning to Theorize the World from Observation
NEO induces compositional latent programs as world theories from observations and executes them to enable explanation-driven generalization.
-
Flexible Multitask Learning with Factorized Diffusion Policy
A factorized modular diffusion policy improves fitting of multimodal robot actions and enables flexible task adaptation without catastrophic forgetting.
-
How Far is Video Generation from World Model: A Physical Law Perspective
Video generation models generalize perfectly inside the training distribution but fail out-of-distribution and rely on case-based mimicking of nearest training examples instead of abstracting physical laws.
-
A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing
Tunable energy landscapes whose thermal averages equal sigmoid, softmax, and matrix-vector products can, in principle, form the basis of a low-energy analog computer, with a superconducting double-well device as a fir...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.