REVIEW 3 cited by
MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimization
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
MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimization
read the original abstract
Diffusion Models have revolutionized the field of human motion generation by offering exceptional generation quality and fine-grained controllability through natural language conditioning. Their inherent stochasticity, that is the ability to generate various outputs from a single input, is key to their success. However, this diversity should not be unrestricted, as it may lead to unlikely generations. Instead, it should be confined within the boundaries of text-aligned and realistic generations. To address this issue, we propose MoDiPO (Motion Diffusion DPO), a novel methodology that leverages Direct Preference Optimization (DPO) to align text-to-motion models. We streamline the laborious and expensive process of gathering human preferences needed in DPO by leveraging AI feedback instead. This enables us to experiment with novel DPO strategies, using both online and offline generated motion-preference pairs. To foster future research we contribute with a motion-preference dataset which we dub Pick-a-Move. We demonstrate, both qualitatively and quantitatively, that our proposed method yields significantly more realistic motions. In particular, MoDiPO substantially improves Frechet Inception Distance (FID) while retaining the same RPrecision and Multi-Modality performances.
Forward citations
Cited by 3 Pith papers
-
SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid Control
A new diffusion transformer policy with joint attention over actions, states, and text plus RL post-training outperforms prior methods on language alignment and motion quality for humanoid control.
-
SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid Control
SCRIPT presents a scalable diffusion policy with JAST-DiT architecture, nonlinear history conditioning, and RLHR post-training that claims to outperform prior methods on text alignment, motion quality, and physical re...
-
IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation
Interleaving motion generation with text-motion assessment and refinement improves alignment between generated human motion and goal text.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.